@markuplint/html-parser 3.0.0-canary.5 → 3.0.0-dev.177

package/README.md

@@ -9,7 +9,7 @@
 <details>
 <summary>If you are installing purposely, how below:</summary>
 
-```sh
+```shell
 $ npm install @markuplint/html-parser
 
 $ yarn add @markuplint/html-parser

package/lib/attr-tokenizer.js

@@ -5,17 +5,18 @@ const reAttrsInStartTag =
 // eslint-disable-next-line no-control-regex
 /(\s*)([^\x00-\x1f\x7f-\x9f "'>/=]+)(?:(\s*)(=)(\s*)(?:(?:"([^"]*)")|(?:'([^']*)')|([^\s]*)))?/;
 function attrTokenizer(raw, line, col, startOffset) {
+    var _a, _b, _c, _d, _e, _f, _g, _h;
     const attrMatchedMap = raw.match(reAttrsInStartTag);
     if (!attrMatchedMap) {
         throw new SyntaxError('Illegal attribute token');
     }
-    const spacesBeforeAttrString = attrMatchedMap[1];
-    const nameChars = attrMatchedMap[2];
-    const spacesBeforeEqualChars = attrMatchedMap[3] || '';
-    const equalChars = attrMatchedMap[4] || null;
-    const spacesAfterEqualChars = attrMatchedMap[5] || '';
+    const spacesBeforeAttrString = (_a = attrMatchedMap[1]) !== null && _a !== void 0 ? _a : '';
+    const nameChars = (_b = attrMatchedMap[2]) !== null && _b !== void 0 ? _b : '';
+    const spacesBeforeEqualChars = (_c = attrMatchedMap[3]) !== null && _c !== void 0 ? _c : '';
+    const equalChars = (_d = attrMatchedMap[4]) !== null && _d !== void 0 ? _d : null;
+    const spacesAfterEqualChars = (_e = attrMatchedMap[5]) !== null && _e !== void 0 ? _e : '';
     const quoteChars = attrMatchedMap[6] != null ? '"' : attrMatchedMap[7] != null ? "'" : null;
-    const valueChars = attrMatchedMap[6] || attrMatchedMap[7] || attrMatchedMap[8] || (quoteChars ? '' : null);
+    const valueChars = (_h = (_g = (_f = attrMatchedMap[6]) !== null && _f !== void 0 ? _f : attrMatchedMap[7]) !== null && _g !== void 0 ? _g : attrMatchedMap[8]) !== null && _h !== void 0 ? _h : (quoteChars ? '' : null);
     let offset = startOffset;
     const spacesBeforeName = (0, parser_utils_1.tokenizer)(spacesBeforeAttrString, line, col, offset);
     line = spacesBeforeName.endLine;
@@ -48,11 +49,11 @@ function attrTokenizer(raw, line, col, startOffset) {
     const endQuote = (0, parser_utils_1.tokenizer)(quoteChars, line, col, offset);
     const attrToken = (0, parser_utils_1.tokenizer)(nameChars +
         spacesBeforeEqualChars +
-        (equalChars || '') +
+        (equalChars !== null && equalChars !== void 0 ? equalChars : '') +
         spacesAfterEqualChars +
-        (quoteChars || '') +
-        (valueChars || '') +
-        (quoteChars || ''), name.startLine, name.startCol, name.startOffset);
+        (quoteChars !== null && quoteChars !== void 0 ? quoteChars : '') +
+        (valueChars !== null && valueChars !== void 0 ? valueChars : '') +
+        (quoteChars !== null && quoteChars !== void 0 ? quoteChars : ''), name.startLine, name.startCol, name.startOffset);
     return {
         type: 'html-attr',
         uuid: (0, parser_utils_1.uuid)(),

package/lib/create-tree.d.ts

@@ -1,2 +1,8 @@
 import type { MLASTNode } from '@markuplint/ml-ast';
-export declare function createTree(rawCode: string, isFragment: boolean, offsetOffset: number, offsetLine: number, offsetColumn: number): MLASTNode[];
+export declare function createTree(
+	rawCode: string,
+	isFragment: boolean,
+	offsetOffset: number,
+	offsetLine: number,
+	offsetColumn: number,
+): MLASTNode[];

package/lib/create-tree.js

@@ -5,15 +5,18 @@ const tslib_1 = require("tslib");
 const parser_utils_1 = require("@markuplint/parser-utils");
 const parse5_1 = require("parse5");
 const parse_raw_tag_1 = tslib_1.__importDefault(require("./parse-raw-tag"));
-const P5_OPTIONS = { sourceCodeLocationInfo: true };
+const P5_OPTIONS = {
+    scriptingEnabled: false,
+    sourceCodeLocationInfo: true,
+};
 function createTree(rawCode, isFragment, offsetOffset, offsetLine, offsetColumn) {
-    const doc = isFragment
-        ? (0, parse5_1.parseFragment)(rawCode, P5_OPTIONS)
-        : (0, parse5_1.parse)(rawCode, P5_OPTIONS);
+    const doc = isFragment ? (0, parse5_1.parseFragment)(rawCode, P5_OPTIONS) : (0, parse5_1.parse)(rawCode, P5_OPTIONS);
     return createTreeRecursive(doc, null, rawCode, offsetOffset, offsetLine, offsetColumn);
 }
 exports.createTree = createTree;
-function createTreeRecursive(rootNode, parentNode, rawHtml, offsetOffset, offsetLine, offsetColumn) {
+function createTreeRecursive(rootNode, 
+// eslint-disable-next-line @typescript-eslint/prefer-readonly-parameter-types
+parentNode, rawHtml, offsetOffset, offsetLine, offsetColumn) {
     const nodeList = [];
     const childNodes = getChildNodes(rootNode);
     let prevNode = null;
@@ -33,11 +36,16 @@ function createTreeRecursive(rootNode, parentNode, rawHtml, offsetOffset, offset
     }
     return nodeList;
 }
-function nodeize(originNode, prevNode, parentNode, rawHtml, offsetOffset, offsetLine, offsetColumn) {
+function nodeize(originNode, 
+// eslint-disable-next-line @typescript-eslint/prefer-readonly-parameter-types
+prevNode, 
+// eslint-disable-next-line @typescript-eslint/prefer-readonly-parameter-types
+parentNode, rawHtml, offsetOffset, offsetLine, offsetColumn) {
+    var _a, _b, _c;
     const nextNode = null;
     const location = getLocation(originNode);
     if (!location) {
-        const prevToken = prevNode || parentNode;
+        const prevToken = prevNode !== null && prevNode !== void 0 ? prevNode : parentNode;
         const startOffset = prevToken ? prevToken.endOffset : 0;
         const endOffset = prevToken ? prevToken.endOffset : 0;
         const startLine = prevToken ? prevToken.endLine : 0;
@@ -72,18 +80,18 @@ function nodeize(originNode, prevNode, parentNode, rawHtml, offsetOffset, offset
         return node;
     }
     const { startOffset, endOffset, startLine, endLine, startCol, endCol } = location;
-    const raw = rawHtml.slice(startOffset, endOffset || startOffset);
+    const raw = rawHtml.slice(startOffset, endOffset !== null && endOffset !== void 0 ? endOffset : startOffset);
     switch (originNode.nodeName) {
         case '#documentType': {
             return {
                 uuid: (0, parser_utils_1.uuid)(),
                 raw,
                 // @ts-ignore
-                name: originNode.name || '',
+                name: (_a = originNode.name) !== null && _a !== void 0 ? _a : '',
                 // @ts-ignore
-                publicId: originNode.publicId || '',
+                publicId: (_b = originNode.publicId) !== null && _b !== void 0 ? _b : '',
                 // @ts-ignore
-                systemId: originNode.systemId || '',
+                systemId: (_c = originNode.systemId) !== null && _c !== void 0 ? _c : '',
                 startOffset: startOffset + offsetOffset,
                 endOffset: endOffset + offsetOffset,
                 startLine: startLine + offsetLine,
@@ -143,7 +151,7 @@ function nodeize(originNode, prevNode, parentNode, rawHtml, offsetOffset, offset
             const tagLoc = 'startTag' in location ? location.startTag : null;
             const startTagRaw = tagLoc
                 ? rawHtml.slice(tagLoc.startOffset, tagLoc.endOffset)
-                : rawHtml.slice(startOffset, endOffset || startOffset);
+                : rawHtml.slice(startOffset, endOffset !== null && endOffset !== void 0 ? endOffset : startOffset);
             const tagTokens = (0, parse_raw_tag_1.default)(startTagRaw, startLine, startCol, startOffset, offsetOffset, offsetLine, offsetColumn);
             const tagName = tagTokens.tagName;
             let endTag = null;
@@ -231,29 +239,10 @@ function nodeize(originNode, prevNode, parentNode, rawHtml, offsetOffset, offset
  * getChildNodes
  *
  * - If node has "content" property then parse as document fragment.
- * - If node is <noscript> then that childNodes is a TextNode. But parse as document fragment it for disabled script.
  */
 function getChildNodes(rootNode) {
-    if (rootNode.nodeName === 'noscript') {
-        const textNode = rootNode.childNodes[0];
-        if (!textNode || textNode.nodeName !== '#text') {
-            return [];
-        }
-        // @ts-ignore
-        const html = textNode.value;
-        // @ts-ignore
-        const { startOffset, startLine, startCol } = textNode.sourceCodeLocation;
-        const breakCount = startLine - 1;
-        const indentWidth = startCol - 1;
-        const offsetSpaces = ' '.repeat(startOffset - Math.max(breakCount, 0) - Math.max(indentWidth, 0)) +
-            '\n'.repeat(breakCount) +
-            ' '.repeat(indentWidth);
-        const fragment = (0, parse5_1.parseFragment)(`${offsetSpaces}${html}`, P5_OPTIONS);
-        const childNodes = fragment.childNodes.slice(offsetSpaces ? 1 : 0);
-        // const childNodes = ('childNodes' in _childNodes && _childNodes.childNodes) || [];
-        return childNodes;
-    }
-    return rootNode.content ? rootNode.content.childNodes : rootNode.childNodes || [];
+    var _a;
+    return rootNode.content ? rootNode.content.childNodes : (_a = rootNode.childNodes) !== null && _a !== void 0 ? _a : [];
 }
 function hasLocation(node) {
     return 'sourceCodeLocation' in node;

package/lib/get-namespace.js

@@ -27,7 +27,7 @@ function getNamespace(tagName, parentNamespace = DEFAULT_NAMESPACE) {
         const doc = (0, parse5_1.parse)(tag);
         node = doc.childNodes[0];
     }
-    if ('namespaceURI' in node) {
+    if (node && 'namespaceURI' in node) {
         return node.namespaceURI;
     }
     return DEFAULT_NAMESPACE;

package/lib/index.d.ts

@@ -1,7 +1,6 @@
+export { default as attrTokenizer } from './attr-tokenizer';
 export { default as isDocumentFragment } from './is-document-fragment';
-export { parse } from './parse';
-export { flattenNodes } from './flatten-nodes';
-export { removeDeprecatedNode } from './remove-deprecated-node';
-export { getNamespace } from './get-namespace';
 export { default as parseRawTag } from './parse-raw-tag';
-export { default as attrTokenizer } from './attr-tokenizer';
+export { getNamespace } from './get-namespace';
+export { parse } from './parse';
+export { createTree } from './create-tree';

package/lib/index.js

@@ -3,18 +3,16 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
     return (mod && mod.__esModule) ? mod : { "default": mod };
 };
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.attrTokenizer = exports.parseRawTag = exports.getNamespace = exports.removeDeprecatedNode = exports.flattenNodes = exports.parse = exports.isDocumentFragment = void 0;
+exports.createTree = exports.parse = exports.getNamespace = exports.parseRawTag = exports.isDocumentFragment = exports.attrTokenizer = void 0;
+var attr_tokenizer_1 = require("./attr-tokenizer");
+Object.defineProperty(exports, "attrTokenizer", { enumerable: true, get: function () { return __importDefault(attr_tokenizer_1).default; } });
 var is_document_fragment_1 = require("./is-document-fragment");
 Object.defineProperty(exports, "isDocumentFragment", { enumerable: true, get: function () { return __importDefault(is_document_fragment_1).default; } });
-var parse_1 = require("./parse");
-Object.defineProperty(exports, "parse", { enumerable: true, get: function () { return parse_1.parse; } });
-var flatten_nodes_1 = require("./flatten-nodes");
-Object.defineProperty(exports, "flattenNodes", { enumerable: true, get: function () { return flatten_nodes_1.flattenNodes; } });
-var remove_deprecated_node_1 = require("./remove-deprecated-node");
-Object.defineProperty(exports, "removeDeprecatedNode", { enumerable: true, get: function () { return remove_deprecated_node_1.removeDeprecatedNode; } });
-var get_namespace_1 = require("./get-namespace");
-Object.defineProperty(exports, "getNamespace", { enumerable: true, get: function () { return get_namespace_1.getNamespace; } });
 var parse_raw_tag_1 = require("./parse-raw-tag");
 Object.defineProperty(exports, "parseRawTag", { enumerable: true, get: function () { return __importDefault(parse_raw_tag_1).default; } });
-var attr_tokenizer_1 = require("./attr-tokenizer");
-Object.defineProperty(exports, "attrTokenizer", { enumerable: true, get: function () { return __importDefault(attr_tokenizer_1).default; } });
+var get_namespace_1 = require("./get-namespace");
+Object.defineProperty(exports, "getNamespace", { enumerable: true, get: function () { return get_namespace_1.getNamespace; } });
+var parse_1 = require("./parse");
+Object.defineProperty(exports, "parse", { enumerable: true, get: function () { return parse_1.parse; } });
+var create_tree_1 = require("./create-tree");
+Object.defineProperty(exports, "createTree", { enumerable: true, get: function () { return create_tree_1.createTree; } });

package/lib/optimize-starts-head-or-body.d.ts

@@ -1,8 +1,11 @@
 import type { MLASTNode } from '@markuplint/ml-ast';
 export declare function isStartsHeadTagOrBodyTag(rawCode: string): boolean;
 export declare function optimizeStartsHeadTagOrBodyTagSetup(rawCode: string): {
-    code: string;
-    heads: string[];
-    bodies: string[];
+	code: string;
+	heads: string[];
+	bodies: string[];
 };
-export declare function optimizeStartsHeadTagOrBodyTagResume(nodeList: MLASTNode[], replacements: ReturnType<typeof optimizeStartsHeadTagOrBodyTagSetup>): void;
+export declare function optimizeStartsHeadTagOrBodyTagResume(
+	nodeList: MLASTNode[],
+	replacements: ReturnType<typeof optimizeStartsHeadTagOrBodyTagSetup>,
+): void;

package/lib/optimize-starts-head-or-body.js

@@ -34,7 +34,11 @@ function optimizeStartsHeadTagOrBodyTagSetup(rawCode) {
     };
 }
 exports.optimizeStartsHeadTagOrBodyTagSetup = optimizeStartsHeadTagOrBodyTagSetup;
-function optimizeStartsHeadTagOrBodyTagResume(nodeList, replacements) {
+function optimizeStartsHeadTagOrBodyTagResume(
+// eslint-disable-next-line @typescript-eslint/prefer-readonly-parameter-types
+nodeList, 
+// eslint-disable-next-line @typescript-eslint/prefer-readonly-parameter-types
+replacements) {
     nodeList.forEach(node => {
         if (!node.nodeName.startsWith(`x-${UNDUPLICATED_CHAR}`)) {
             return;

package/lib/parse-raw-tag.d.ts

@@ -1,9 +1,17 @@
 import type { MLASTAttr, MLToken } from '@markuplint/ml-ast';
 type TagTokens = {
-    tagName: string;
-    attrs: MLASTAttr[];
-    selfClosingSolidus: MLToken;
-    endSpace: MLToken;
+	tagName: string;
+	attrs: MLASTAttr[];
+	selfClosingSolidus: MLToken;
+	endSpace: MLToken;
 };
-export default function parseRawTag(raw: string, startLine: number, startCol: number, startOffset: number, offsetOffset?: number, offsetLine?: number, offsetColumn?: number): TagTokens;
+export default function parseRawTag(
+	raw: string,
+	startLine: number,
+	startCol: number,
+	startOffset: number,
+	offsetOffset?: number,
+	offsetLine?: number,
+	offsetColumn?: number,
+): TagTokens;
 export {};

package/lib/parse-raw-tag.js

@@ -3,23 +3,23 @@ Object.defineProperty(exports, "__esModule", { value: true });
 const tslib_1 = require("tslib");
 const parser_utils_1 = require("@markuplint/parser-utils");
 const attr_tokenizer_1 = tslib_1.__importDefault(require("./attr-tokenizer"));
-const const_1 = require("./const");
 // eslint-disable-next-line no-control-regex
 const reAttrsInStartTag = /\s*[^\x00-\x1f\x7f-\x9f "'>/=]+(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^\s]*))?/;
 const reEndTokens = /(\s*\/)?(\s*)>$/;
 function parseRawTag(raw, startLine, startCol, startOffset, offsetOffset = 0, offsetLine = 0, offsetColumn = 0) {
+    var _a, _b;
     let offset = startOffset + offsetOffset;
     let line = startLine + offsetLine;
     let col = startCol + (startLine === 1 ? offsetColumn : 0);
-    const matches = raw.match(const_1.reTag);
-    if (!matches) {
+    const matches = raw.match(parser_utils_1.reTag);
+    const tagWithAttrs = matches === null || matches === void 0 ? void 0 : matches[1];
+    if (!tagWithAttrs) {
         throw new SyntaxError(`Invalid tag syntax: "${raw}"`);
     }
-    const tagWithAttrs = matches[1];
     // eslint-disable-next-line no-control-regex
     const tagNameSplitted = tagWithAttrs.split(/[\u0000\u0009\u000A\u000C\u0020/>]/);
     const tagName = tagNameSplitted[0] || tagNameSplitted[1];
-    if (!tagName || (!const_1.reTagName.test(tagName) && !(0, parser_utils_1.isPotentialCustomElementName)(tagName))) {
+    if (!tagName || (!parser_utils_1.reTagName.test(tagName) && !(0, parser_utils_1.isPotentialCustomElementName)(tagName))) {
         throw new SyntaxError(`Invalid tag name: "${tagName}" in <${tagWithAttrs}>`);
     }
     const tagStartPos = tagWithAttrs.indexOf(tagName);
@@ -41,11 +41,11 @@ function parseRawTag(raw, startLine, startCol, startOffset, offsetOffset = 0, of
         }
     }
     const endTokens = reEndTokens.exec(raw);
-    const selfClosingSolidus = (0, parser_utils_1.tokenizer)(endTokens && endTokens[1], line, col, offset);
+    const selfClosingSolidus = (0, parser_utils_1.tokenizer)((_a = endTokens === null || endTokens === void 0 ? void 0 : endTokens[1]) !== null && _a !== void 0 ? _a : '', line, col, offset);
     line = selfClosingSolidus.endLine;
     col = selfClosingSolidus.endCol;
     offset = selfClosingSolidus.endOffset;
-    const endSpace = (0, parser_utils_1.tokenizer)(endTokens && endTokens[2], line, col, offset);
+    const endSpace = (0, parser_utils_1.tokenizer)((_b = endTokens === null || endTokens === void 0 ? void 0 : endTokens[2]) !== null && _b !== void 0 ? _b : '', line, col, offset);
     return {
         tagName,
         attrs,

package/lib/parse.js

@@ -4,7 +4,6 @@ exports.parse = void 0;
 const tslib_1 = require("tslib");
 const parser_utils_1 = require("@markuplint/parser-utils");
 const create_tree_1 = require("./create-tree");
-const flatten_nodes_1 = require("./flatten-nodes");
 const is_document_fragment_1 = tslib_1.__importDefault(require("./is-document-fragment"));
 const optimize_starts_head_or_body_1 = require("./optimize-starts-head-or-body");
 const parse = (rawCode, options) => {
@@ -18,7 +17,7 @@ const parse = (rawCode, options) => {
         rawCode = data.code;
     }
     const nodeTree = (0, create_tree_1.createTree)(rawCode, isFragment, (_a = options === null || options === void 0 ? void 0 : options.offsetOffset) !== null && _a !== void 0 ? _a : 0, (_b = options === null || options === void 0 ? void 0 : options.offsetLine) !== null && _b !== void 0 ? _b : 0, (_c = options === null || options === void 0 ? void 0 : options.offsetColumn) !== null && _c !== void 0 ? _c : 0);
-    const nodeList = (0, flatten_nodes_1.flattenNodes)(nodeTree, rawCode);
+    const nodeList = (0, parser_utils_1.flattenNodes)(nodeTree, rawCode);
     if (data) {
         (0, optimize_starts_head_or_body_1.optimizeStartsHeadTagOrBodyTagResume)(nodeList, data);
     }

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@markuplint/html-parser",
-	"version": "3.0.0-canary.5+382d1365",
+	"version": "3.0.0-dev.177+e94f3601",
 	"description": "HTML parser for markuplint",
 	"repository": "git@github.com:markuplint/markuplint.git",
 	"author": "Yusuke Hirao <yusukehirao@me.com>",
@@ -11,16 +11,20 @@
 	"publishConfig": {
 		"access": "public"
 	},
+	"typedoc": {
+		"entryPoint": "./src/index.ts"
+	},
 	"scripts": {
 		"build": "tsc",
 		"dev": "tsc --build --watch",
 		"clean": "tsc --build --clean"
 	},
 	"dependencies": {
-		"@markuplint/ml-ast": "3.0.0-canary.69+382d1365",
-		"@markuplint/parser-utils": "3.0.0-canary.5+382d1365",
-		"parse5": "6",
-		"tslib": "^2.4.0"
+		"@markuplint/ml-ast": "3.0.0-dev.177+e94f3601",
+		"@markuplint/parser-utils": "3.0.0-dev.177+e94f3601",
+		"parse5": "7.1.2",
+		"tslib": "^2.4.1",
+		"type-fest": "^3.8.0"
 	},
-	"gitHead": "382d13653071bd02210d5430403d1a87c840398c"
+	"gitHead": "e94f3601bf93366d1a2c7385ff7235817d82f7c9"
 }