Add extracted source directory and README navigation

This commit is contained in:
Shawn Bot
2026-03-31 14:56:06 +00:00
parent 6252bb6eb5
commit 91e01d755b
4757 changed files with 984951 additions and 0 deletions

View File

@@ -0,0 +1,348 @@
'use strict';
const doctype = require('parse5/lib/common/doctype');
const { DOCUMENT_MODE } = require('parse5/lib/common/html');
//Conversion tables for DOM Level1 structure emulation
const nodeTypes = {
element: 1,
text: 3,
cdata: 4,
comment: 8
};
const nodePropertyShorthands = {
tagName: 'name',
childNodes: 'children',
parentNode: 'parent',
previousSibling: 'prev',
nextSibling: 'next',
nodeValue: 'data'
};
//Node
class Node {
constructor(props) {
for (const key of Object.keys(props)) {
this[key] = props[key];
}
}
get firstChild() {
const children = this.children;
return (children && children[0]) || null;
}
get lastChild() {
const children = this.children;
return (children && children[children.length - 1]) || null;
}
get nodeType() {
return nodeTypes[this.type] || nodeTypes.element;
}
}
Object.keys(nodePropertyShorthands).forEach(key => {
const shorthand = nodePropertyShorthands[key];
Object.defineProperty(Node.prototype, key, {
get: function() {
return this[shorthand] || null;
},
set: function(val) {
this[shorthand] = val;
return val;
}
});
});
//Node construction
exports.createDocument = function() {
return new Node({
type: 'root',
name: 'root',
parent: null,
prev: null,
next: null,
children: [],
'x-mode': DOCUMENT_MODE.NO_QUIRKS
});
};
exports.createDocumentFragment = function() {
return new Node({
type: 'root',
name: 'root',
parent: null,
prev: null,
next: null,
children: []
});
};
exports.createElement = function(tagName, namespaceURI, attrs) {
const attribs = Object.create(null);
const attribsNamespace = Object.create(null);
const attribsPrefix = Object.create(null);
for (let i = 0; i < attrs.length; i++) {
const attrName = attrs[i].name;
attribs[attrName] = attrs[i].value;
attribsNamespace[attrName] = attrs[i].namespace;
attribsPrefix[attrName] = attrs[i].prefix;
}
return new Node({
type: tagName === 'script' || tagName === 'style' ? tagName : 'tag',
name: tagName,
namespace: namespaceURI,
attribs: attribs,
'x-attribsNamespace': attribsNamespace,
'x-attribsPrefix': attribsPrefix,
children: [],
parent: null,
prev: null,
next: null
});
};
exports.createCommentNode = function(data) {
return new Node({
type: 'comment',
data: data,
parent: null,
prev: null,
next: null
});
};
const createTextNode = function(value) {
return new Node({
type: 'text',
data: value,
parent: null,
prev: null,
next: null
});
};
//Tree mutation
const appendChild = (exports.appendChild = function(parentNode, newNode) {
const prev = parentNode.children[parentNode.children.length - 1];
if (prev) {
prev.next = newNode;
newNode.prev = prev;
}
parentNode.children.push(newNode);
newNode.parent = parentNode;
});
const insertBefore = (exports.insertBefore = function(parentNode, newNode, referenceNode) {
const insertionIdx = parentNode.children.indexOf(referenceNode);
const prev = referenceNode.prev;
if (prev) {
prev.next = newNode;
newNode.prev = prev;
}
referenceNode.prev = newNode;
newNode.next = referenceNode;
parentNode.children.splice(insertionIdx, 0, newNode);
newNode.parent = parentNode;
});
exports.setTemplateContent = function(templateElement, contentElement) {
appendChild(templateElement, contentElement);
};
exports.getTemplateContent = function(templateElement) {
return templateElement.children[0];
};
exports.setDocumentType = function(document, name, publicId, systemId) {
const data = doctype.serializeContent(name, publicId, systemId);
let doctypeNode = null;
for (let i = 0; i < document.children.length; i++) {
if (document.children[i].type === 'directive' && document.children[i].name === '!doctype') {
doctypeNode = document.children[i];
break;
}
}
if (doctypeNode) {
doctypeNode.data = data;
doctypeNode['x-name'] = name;
doctypeNode['x-publicId'] = publicId;
doctypeNode['x-systemId'] = systemId;
} else {
appendChild(
document,
new Node({
type: 'directive',
name: '!doctype',
data: data,
'x-name': name,
'x-publicId': publicId,
'x-systemId': systemId
})
);
}
};
exports.setDocumentMode = function(document, mode) {
document['x-mode'] = mode;
};
exports.getDocumentMode = function(document) {
return document['x-mode'];
};
exports.detachNode = function(node) {
if (node.parent) {
const idx = node.parent.children.indexOf(node);
const prev = node.prev;
const next = node.next;
node.prev = null;
node.next = null;
if (prev) {
prev.next = next;
}
if (next) {
next.prev = prev;
}
node.parent.children.splice(idx, 1);
node.parent = null;
}
};
exports.insertText = function(parentNode, text) {
const lastChild = parentNode.children[parentNode.children.length - 1];
if (lastChild && lastChild.type === 'text') {
lastChild.data += text;
} else {
appendChild(parentNode, createTextNode(text));
}
};
exports.insertTextBefore = function(parentNode, text, referenceNode) {
const prevNode = parentNode.children[parentNode.children.indexOf(referenceNode) - 1];
if (prevNode && prevNode.type === 'text') {
prevNode.data += text;
} else {
insertBefore(parentNode, createTextNode(text), referenceNode);
}
};
exports.adoptAttributes = function(recipient, attrs) {
for (let i = 0; i < attrs.length; i++) {
const attrName = attrs[i].name;
if (typeof recipient.attribs[attrName] === 'undefined') {
recipient.attribs[attrName] = attrs[i].value;
recipient['x-attribsNamespace'][attrName] = attrs[i].namespace;
recipient['x-attribsPrefix'][attrName] = attrs[i].prefix;
}
}
};
//Tree traversing
exports.getFirstChild = function(node) {
return node.children[0];
};
exports.getChildNodes = function(node) {
return node.children;
};
exports.getParentNode = function(node) {
return node.parent;
};
exports.getAttrList = function(element) {
const attrList = [];
for (const name in element.attribs) {
attrList.push({
name: name,
value: element.attribs[name],
namespace: element['x-attribsNamespace'][name],
prefix: element['x-attribsPrefix'][name]
});
}
return attrList;
};
//Node data
exports.getTagName = function(element) {
return element.name;
};
exports.getNamespaceURI = function(element) {
return element.namespace;
};
exports.getTextNodeContent = function(textNode) {
return textNode.data;
};
exports.getCommentNodeContent = function(commentNode) {
return commentNode.data;
};
exports.getDocumentTypeNodeName = function(doctypeNode) {
return doctypeNode['x-name'];
};
exports.getDocumentTypeNodePublicId = function(doctypeNode) {
return doctypeNode['x-publicId'];
};
exports.getDocumentTypeNodeSystemId = function(doctypeNode) {
return doctypeNode['x-systemId'];
};
//Node types
exports.isTextNode = function(node) {
return node.type === 'text';
};
exports.isCommentNode = function(node) {
return node.type === 'comment';
};
exports.isDocumentTypeNode = function(node) {
return node.type === 'directive' && node.name === '!doctype';
};
exports.isElementNode = function(node) {
return !!node.attribs;
};
// Source code location
exports.setNodeSourceCodeLocation = function(node, location) {
node.sourceCodeLocation = location;
};
exports.getNodeSourceCodeLocation = function(node) {
return node.sourceCodeLocation;
};
exports.updateNodeSourceCodeLocation = function(node, endLocation) {
node.sourceCodeLocation = Object.assign(node.sourceCodeLocation, endLocation);
};

View File

@@ -0,0 +1,162 @@
'use strict';
const { DOCUMENT_MODE } = require('./html');
//Const
const VALID_DOCTYPE_NAME = 'html';
const VALID_SYSTEM_ID = 'about:legacy-compat';
const QUIRKS_MODE_SYSTEM_ID = 'http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd';
const QUIRKS_MODE_PUBLIC_ID_PREFIXES = [
'+//silmaril//dtd html pro v0r11 19970101//',
'-//as//dtd html 3.0 aswedit + extensions//',
'-//advasoft ltd//dtd html 3.0 aswedit + extensions//',
'-//ietf//dtd html 2.0 level 1//',
'-//ietf//dtd html 2.0 level 2//',
'-//ietf//dtd html 2.0 strict level 1//',
'-//ietf//dtd html 2.0 strict level 2//',
'-//ietf//dtd html 2.0 strict//',
'-//ietf//dtd html 2.0//',
'-//ietf//dtd html 2.1e//',
'-//ietf//dtd html 3.0//',
'-//ietf//dtd html 3.2 final//',
'-//ietf//dtd html 3.2//',
'-//ietf//dtd html 3//',
'-//ietf//dtd html level 0//',
'-//ietf//dtd html level 1//',
'-//ietf//dtd html level 2//',
'-//ietf//dtd html level 3//',
'-//ietf//dtd html strict level 0//',
'-//ietf//dtd html strict level 1//',
'-//ietf//dtd html strict level 2//',
'-//ietf//dtd html strict level 3//',
'-//ietf//dtd html strict//',
'-//ietf//dtd html//',
'-//metrius//dtd metrius presentational//',
'-//microsoft//dtd internet explorer 2.0 html strict//',
'-//microsoft//dtd internet explorer 2.0 html//',
'-//microsoft//dtd internet explorer 2.0 tables//',
'-//microsoft//dtd internet explorer 3.0 html strict//',
'-//microsoft//dtd internet explorer 3.0 html//',
'-//microsoft//dtd internet explorer 3.0 tables//',
'-//netscape comm. corp.//dtd html//',
'-//netscape comm. corp.//dtd strict html//',
"-//o'reilly and associates//dtd html 2.0//",
"-//o'reilly and associates//dtd html extended 1.0//",
"-//o'reilly and associates//dtd html extended relaxed 1.0//",
'-//sq//dtd html 2.0 hotmetal + extensions//',
'-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//',
'-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//',
'-//spyglass//dtd html 2.0 extended//',
'-//sun microsystems corp.//dtd hotjava html//',
'-//sun microsystems corp.//dtd hotjava strict html//',
'-//w3c//dtd html 3 1995-03-24//',
'-//w3c//dtd html 3.2 draft//',
'-//w3c//dtd html 3.2 final//',
'-//w3c//dtd html 3.2//',
'-//w3c//dtd html 3.2s draft//',
'-//w3c//dtd html 4.0 frameset//',
'-//w3c//dtd html 4.0 transitional//',
'-//w3c//dtd html experimental 19960712//',
'-//w3c//dtd html experimental 970421//',
'-//w3c//dtd w3 html//',
'-//w3o//dtd w3 html 3.0//',
'-//webtechs//dtd mozilla html 2.0//',
'-//webtechs//dtd mozilla html//'
];
const QUIRKS_MODE_NO_SYSTEM_ID_PUBLIC_ID_PREFIXES = QUIRKS_MODE_PUBLIC_ID_PREFIXES.concat([
'-//w3c//dtd html 4.01 frameset//',
'-//w3c//dtd html 4.01 transitional//'
]);
const QUIRKS_MODE_PUBLIC_IDS = ['-//w3o//dtd w3 html strict 3.0//en//', '-/w3c/dtd html 4.0 transitional/en', 'html'];
const LIMITED_QUIRKS_PUBLIC_ID_PREFIXES = ['-//w3c//dtd xhtml 1.0 frameset//', '-//w3c//dtd xhtml 1.0 transitional//'];
const LIMITED_QUIRKS_WITH_SYSTEM_ID_PUBLIC_ID_PREFIXES = LIMITED_QUIRKS_PUBLIC_ID_PREFIXES.concat([
'-//w3c//dtd html 4.01 frameset//',
'-//w3c//dtd html 4.01 transitional//'
]);
//Utils
function enquoteDoctypeId(id) {
const quote = id.indexOf('"') !== -1 ? "'" : '"';
return quote + id + quote;
}
function hasPrefix(publicId, prefixes) {
for (let i = 0; i < prefixes.length; i++) {
if (publicId.indexOf(prefixes[i]) === 0) {
return true;
}
}
return false;
}
//API
exports.isConforming = function(token) {
return (
token.name === VALID_DOCTYPE_NAME &&
token.publicId === null &&
(token.systemId === null || token.systemId === VALID_SYSTEM_ID)
);
};
exports.getDocumentMode = function(token) {
if (token.name !== VALID_DOCTYPE_NAME) {
return DOCUMENT_MODE.QUIRKS;
}
const systemId = token.systemId;
if (systemId && systemId.toLowerCase() === QUIRKS_MODE_SYSTEM_ID) {
return DOCUMENT_MODE.QUIRKS;
}
let publicId = token.publicId;
if (publicId !== null) {
publicId = publicId.toLowerCase();
if (QUIRKS_MODE_PUBLIC_IDS.indexOf(publicId) > -1) {
return DOCUMENT_MODE.QUIRKS;
}
let prefixes = systemId === null ? QUIRKS_MODE_NO_SYSTEM_ID_PUBLIC_ID_PREFIXES : QUIRKS_MODE_PUBLIC_ID_PREFIXES;
if (hasPrefix(publicId, prefixes)) {
return DOCUMENT_MODE.QUIRKS;
}
prefixes =
systemId === null ? LIMITED_QUIRKS_PUBLIC_ID_PREFIXES : LIMITED_QUIRKS_WITH_SYSTEM_ID_PUBLIC_ID_PREFIXES;
if (hasPrefix(publicId, prefixes)) {
return DOCUMENT_MODE.LIMITED_QUIRKS;
}
}
return DOCUMENT_MODE.NO_QUIRKS;
};
exports.serializeContent = function(name, publicId, systemId) {
let str = '!DOCTYPE ';
if (name) {
str += name;
}
if (publicId) {
str += ' PUBLIC ' + enquoteDoctypeId(publicId);
} else if (systemId) {
str += ' SYSTEM';
}
if (systemId !== null) {
str += ' ' + enquoteDoctypeId(systemId);
}
return str;
};

View File

@@ -0,0 +1,272 @@
'use strict';
const NS = (exports.NAMESPACES = {
HTML: 'http://www.w3.org/1999/xhtml',
MATHML: 'http://www.w3.org/1998/Math/MathML',
SVG: 'http://www.w3.org/2000/svg',
XLINK: 'http://www.w3.org/1999/xlink',
XML: 'http://www.w3.org/XML/1998/namespace',
XMLNS: 'http://www.w3.org/2000/xmlns/'
});
exports.ATTRS = {
TYPE: 'type',
ACTION: 'action',
ENCODING: 'encoding',
PROMPT: 'prompt',
NAME: 'name',
COLOR: 'color',
FACE: 'face',
SIZE: 'size'
};
exports.DOCUMENT_MODE = {
NO_QUIRKS: 'no-quirks',
QUIRKS: 'quirks',
LIMITED_QUIRKS: 'limited-quirks'
};
const $ = (exports.TAG_NAMES = {
A: 'a',
ADDRESS: 'address',
ANNOTATION_XML: 'annotation-xml',
APPLET: 'applet',
AREA: 'area',
ARTICLE: 'article',
ASIDE: 'aside',
B: 'b',
BASE: 'base',
BASEFONT: 'basefont',
BGSOUND: 'bgsound',
BIG: 'big',
BLOCKQUOTE: 'blockquote',
BODY: 'body',
BR: 'br',
BUTTON: 'button',
CAPTION: 'caption',
CENTER: 'center',
CODE: 'code',
COL: 'col',
COLGROUP: 'colgroup',
DD: 'dd',
DESC: 'desc',
DETAILS: 'details',
DIALOG: 'dialog',
DIR: 'dir',
DIV: 'div',
DL: 'dl',
DT: 'dt',
EM: 'em',
EMBED: 'embed',
FIELDSET: 'fieldset',
FIGCAPTION: 'figcaption',
FIGURE: 'figure',
FONT: 'font',
FOOTER: 'footer',
FOREIGN_OBJECT: 'foreignObject',
FORM: 'form',
FRAME: 'frame',
FRAMESET: 'frameset',
H1: 'h1',
H2: 'h2',
H3: 'h3',
H4: 'h4',
H5: 'h5',
H6: 'h6',
HEAD: 'head',
HEADER: 'header',
HGROUP: 'hgroup',
HR: 'hr',
HTML: 'html',
I: 'i',
IMG: 'img',
IMAGE: 'image',
INPUT: 'input',
IFRAME: 'iframe',
KEYGEN: 'keygen',
LABEL: 'label',
LI: 'li',
LINK: 'link',
LISTING: 'listing',
MAIN: 'main',
MALIGNMARK: 'malignmark',
MARQUEE: 'marquee',
MATH: 'math',
MENU: 'menu',
META: 'meta',
MGLYPH: 'mglyph',
MI: 'mi',
MO: 'mo',
MN: 'mn',
MS: 'ms',
MTEXT: 'mtext',
NAV: 'nav',
NOBR: 'nobr',
NOFRAMES: 'noframes',
NOEMBED: 'noembed',
NOSCRIPT: 'noscript',
OBJECT: 'object',
OL: 'ol',
OPTGROUP: 'optgroup',
OPTION: 'option',
P: 'p',
PARAM: 'param',
PLAINTEXT: 'plaintext',
PRE: 'pre',
RB: 'rb',
RP: 'rp',
RT: 'rt',
RTC: 'rtc',
RUBY: 'ruby',
S: 's',
SCRIPT: 'script',
SECTION: 'section',
SELECT: 'select',
SOURCE: 'source',
SMALL: 'small',
SPAN: 'span',
STRIKE: 'strike',
STRONG: 'strong',
STYLE: 'style',
SUB: 'sub',
SUMMARY: 'summary',
SUP: 'sup',
TABLE: 'table',
TBODY: 'tbody',
TEMPLATE: 'template',
TEXTAREA: 'textarea',
TFOOT: 'tfoot',
TD: 'td',
TH: 'th',
THEAD: 'thead',
TITLE: 'title',
TR: 'tr',
TRACK: 'track',
TT: 'tt',
U: 'u',
UL: 'ul',
SVG: 'svg',
VAR: 'var',
WBR: 'wbr',
XMP: 'xmp'
});
exports.SPECIAL_ELEMENTS = {
[NS.HTML]: {
[$.ADDRESS]: true,
[$.APPLET]: true,
[$.AREA]: true,
[$.ARTICLE]: true,
[$.ASIDE]: true,
[$.BASE]: true,
[$.BASEFONT]: true,
[$.BGSOUND]: true,
[$.BLOCKQUOTE]: true,
[$.BODY]: true,
[$.BR]: true,
[$.BUTTON]: true,
[$.CAPTION]: true,
[$.CENTER]: true,
[$.COL]: true,
[$.COLGROUP]: true,
[$.DD]: true,
[$.DETAILS]: true,
[$.DIR]: true,
[$.DIV]: true,
[$.DL]: true,
[$.DT]: true,
[$.EMBED]: true,
[$.FIELDSET]: true,
[$.FIGCAPTION]: true,
[$.FIGURE]: true,
[$.FOOTER]: true,
[$.FORM]: true,
[$.FRAME]: true,
[$.FRAMESET]: true,
[$.H1]: true,
[$.H2]: true,
[$.H3]: true,
[$.H4]: true,
[$.H5]: true,
[$.H6]: true,
[$.HEAD]: true,
[$.HEADER]: true,
[$.HGROUP]: true,
[$.HR]: true,
[$.HTML]: true,
[$.IFRAME]: true,
[$.IMG]: true,
[$.INPUT]: true,
[$.LI]: true,
[$.LINK]: true,
[$.LISTING]: true,
[$.MAIN]: true,
[$.MARQUEE]: true,
[$.MENU]: true,
[$.META]: true,
[$.NAV]: true,
[$.NOEMBED]: true,
[$.NOFRAMES]: true,
[$.NOSCRIPT]: true,
[$.OBJECT]: true,
[$.OL]: true,
[$.P]: true,
[$.PARAM]: true,
[$.PLAINTEXT]: true,
[$.PRE]: true,
[$.SCRIPT]: true,
[$.SECTION]: true,
[$.SELECT]: true,
[$.SOURCE]: true,
[$.STYLE]: true,
[$.SUMMARY]: true,
[$.TABLE]: true,
[$.TBODY]: true,
[$.TD]: true,
[$.TEMPLATE]: true,
[$.TEXTAREA]: true,
[$.TFOOT]: true,
[$.TH]: true,
[$.THEAD]: true,
[$.TITLE]: true,
[$.TR]: true,
[$.TRACK]: true,
[$.UL]: true,
[$.WBR]: true,
[$.XMP]: true
},
[NS.MATHML]: {
[$.MI]: true,
[$.MO]: true,
[$.MN]: true,
[$.MS]: true,
[$.MTEXT]: true,
[$.ANNOTATION_XML]: true
},
[NS.SVG]: {
[$.TITLE]: true,
[$.FOREIGN_OBJECT]: true,
[$.DESC]: true
}
};