wikiparser-node 0.2.1 → 0.2.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wikiparser-node",
-  "version": "0.2.1",
+  "version": "0.2.2",
   "description": "A Node.js parser for MediaWiki markup with AST",
   "keywords": [
     "mediawiki",

package/parser/table.js

@@ -12,6 +12,7 @@ const parseTable = ({firstChild, type}, config = Parser.getConfig(), accum = [])
 		TableToken = require('../src/table'),
 		TrToken = require('../src/table/tr'),
 		TdToken = require('../src/table/td'),
+		DdToken = require('../src/nowiki/dd'),
 		/** @type {TrToken[]} */ stack = [],
 		lines = firstChild.split('\n');
 	let out = type === 'root' ? '' : `\n${lines.shift()}`;
@@ -33,10 +34,13 @@ const parseTable = ({firstChild, type}, config = Parser.getConfig(), accum = [])
 		let top = stack.pop();
 		const [spaces] = outLine.match(/^(?:\s|\x00\d+c\x7f)*/);
 		const line = outLine.slice(spaces.length),
-			matchesStart = line.match(/^(:*(?:\s|\x00\d+c\x7f)*)({\||{\x00\d+!\x7f|\x00\d+{\x7f)(.*)/);
+			matchesStart = line.match(/^(:*)((?:\s|\x00\d+c\x7f)*)({\||{\x00\d+!\x7f|\x00\d+{\x7f)(.*)/);
 		if (matchesStart) {
-			const [, indent, tableSyntax, attr] = matchesStart;
-			push(`\n${spaces}${indent}\x00${accum.length}b\x7f`, top);
+			const [, indent, moreSpaces, tableSyntax, attr] = matchesStart;
+			if (indent) {
+				new DdToken(indent, config, accum);
+			}
+			push(`\n${spaces}${indent && `\x00${accum.length - 1}d\x7f`}${moreSpaces}\x00${accum.length}b\x7f`, top);
 			const table = new TableToken(tableSyntax, attr, config, accum);
 			stack.push(...top ? [top] : [], table);
 			continue;

package/src/attribute.js

@@ -108,31 +108,24 @@ class AttributeToken extends Token {
 		return super.getAttribute(key);
 	}
 
-	/** @complexity `n` */
-	build() {
-		super.build();
-		if (this.type === 'ext-attr') {
-			return this;
-		}
-		for (let [key, text] of this.#attr) {
-			let built = false;
-			if (key.includes('\x00')) {
-				this.#attr.delete(key);
-				key = this.buildFromStr(key).map(String).join('');
-				built = true;
-			}
-			if (typeof text === 'string' && text.includes('\x00')) {
-				text = this.buildFromStr(text).map(String).join('');
-				built = true;
-			}
-			if (built) {
-				this.#attr.set(key, text);
+	afterBuild() {
+		if (this.type !== 'ext-attr') {
+			for (let [key, text] of this.#attr) {
+				let built = false;
+				if (key.includes('\x00')) {
+					this.#attr.delete(key);
+					key = this.buildFromStr(key).map(String).join('');
+					built = true;
+				}
+				if (typeof text === 'string' && text.includes('\x00')) {
+					text = this.buildFromStr(text).map(String).join('');
+					built = true;
+				}
+				if (built) {
+					this.#attr.set(key, text);
+				}
 			}
 		}
-		return this;
-	}
-
-	afterBuild() {
 		const that = this,
 			/** @type {AstListener} */ attributeListener = ({type, target}) => {
 				if (type === 'text' || target !== that) {

package/src/converterFlags.js

@@ -39,6 +39,7 @@ class ConverterFlagsToken extends Token {
 				}
 			};
 		this.addEventListener(['remove', 'insert', 'text', 'replace'], converterFlagsListener);
+		return this;
 	}
 
 	/**

package/src/converterRule.js

@@ -77,6 +77,7 @@ class ConverterRuleToken extends Token {
 				}
 			};
 		this.addEventListener(['remove', 'insert', 'text', 'replace'], converterRuleListener);
+		return this;
 	}
 
 	/**

package/src/extLink.js

@@ -116,7 +116,7 @@ class ExtLinkToken extends Token {
 		if (this.childNodes.length === 1) {
 			this.appendChild(lastChild);
 		} else {
-			this.lastElementChild.replaceWith(lastChild);
+			this.lastElementChild.safeReplaceWith(lastChild);
 		}
 		this.#space ||= ' ';
 	}

package/src/index.js

@@ -51,11 +51,8 @@ const {externalUse} = require('../util/debug'),
 class Token extends AstElement {
 	type = 'root';
 	/** 解析阶段，参见顶部注释。只对plain Token有意义。 */ #stage = 0;
-	/** @type {ParserConfig} */ #config;
-	/**
-	 * 这个数组起两个作用：1. 数组中的Token会在build时替换`/\x00\d+.\x7f/`标记；2. 数组中的Token会依次执行parseOnce和build方法。
-	 * @type {accum}
-	 */
+	#config;
+	/** 这个数组起两个作用：1. 数组中的Token会在build时替换`/\x00\d+.\x7f/`标记；2. 数组中的Token会依次执行parseOnce和build方法。 */
 	#accum;
 	/** @type {Record<string, Ranges>} */ #acceptable;
 	#protectedChildren = new Ranges();
@@ -71,7 +68,9 @@ class Token extends AstElement {
 		if (typeof wikitext === 'string') {
 			this.appendChild(halfParsed ? wikitext : wikitext.replace(/[\x00\x7f]/g, ''));
 		}
-		this.setAttribute('config', config).setAttribute('accum', accum).setAttribute('acceptable', acceptable);
+		this.#config = config;
+		this.#accum = accum;
+		this.setAttribute('acceptable', acceptable);
 		accum.push(this);
 	}
 

package/src/link/category.js

@@ -37,6 +37,7 @@ class CategoryToken extends LinkToken {
 			}
 		};
 		this.addEventListener(['remove', 'insert', 'replace', 'text'], categoryListener);
+		return this;
 	}
 
 	#updateSortkey() {

package/src/magicLink.js

@@ -42,10 +42,14 @@ class MagicLinkToken extends Token {
 		if (parameter?.getValue() === this.text()) {
 			this.replaceWith(this.toString());
 		}
+		return this;
 	}
 
 	getUrl() {
-		const url = this.text();
+		let url = this.text();
+		if (url.startsWith('//')) {
+			url = `https:${url}`;
+		}
 		try {
 			return new URL(url);
 		} catch (e) {

package/src/nowiki/dd.js

@@ -9,10 +9,10 @@ const /** @type {Parser} */ Parser = require('../..'),
  */
 class DdToken extends NowikiToken {
 	type = 'dd';
-	dt;
-	ul;
-	ol;
-	indent;
+	dt = false;
+	ul = false;
+	ol = false;
+	indent = 0;
 
 	/** @param {string} str */
 	#update(str) {

package/src/table/td.js

@@ -152,7 +152,7 @@ class TdToken extends fixedToken(TrToken) {
 		return this;
 	}
 
-	build() {
+	afterBuild() {
 		if (this.#innerSyntax.includes('\x00')) {
 			this.#innerSyntax = this.buildFromStr(this.#innerSyntax).map(String).join('');
 		}

package/src/tagPair/index.js

@@ -57,7 +57,7 @@ class TagPairToken extends fixedToken(Token) {
 		}
 		return selfClosing
 			? `<${opening}${String(firstChild)}/>`
-			: `<${opening}${String(firstChild)}>${String(lastChild)}${closed ? `</${closing}>` : ''}`;
+			: `<${opening}${String(firstChild)}>${String(lastChild)}${this.closed ? `</${closing}>` : ''}`;
 	}
 
 	getPadding() {

package/util/string.js

@@ -70,6 +70,6 @@ const normalizeSpace = (token = '', separator = '') => {
 };
 
 const extUrlChar = '(?:[\\d.]+|\\[[\\da-f:.]+\\]|[^[\\]<>"\\x00-\\x20\\x7f\\p{Zs}\\ufffd])'
-	+ '[^[\\]<>"\\x00-\\x20\\x7f\\p{Zs}\\ufffd]*';
+	+ '(?:[^[\\]<>"\\x00-\\x20\\x7f\\p{Zs}\\ufffd]|\\x00\\d+c\\x7f)*';
 
 module.exports = {toCase, removeComment, ucfirst, escapeRegExp, text, explode, noWrap, normalizeSpace, extUrlChar};

package/errors/2022-07-04T22:30:41.785Z

@@ -1 +0,0 @@
-{|

package/errors/2022-07-04T22:30:41.785Z.err

@@ -1,11 +0,0 @@
-TypeError: normalizeSpace is not a function
-    at AttributeToken.toString (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/src/attribute.js:249:44)
-    at #parseAttr (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/src/attribute.js:58:21)
-    at new AttributeToken (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/src/attribute.js:87:45)
-    at new TrToken (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/src/table/tr.js:28:4)
-    at new TableToken (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/src/table/index.js:66:3)
-    at parseTable (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/parser/table.js:40:18)
-    at #parseTable (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/src/index.js:553:16)
-    at Token.parseOnce (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/src/index.js:431:21)
-    at Token.parse (/Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/src/index.js:526:9)
-    at /Users/mengxiwu/Documents/CCM-RP/node/wikiparser-node/index.js:134:11

package/errors/2022-07-04T22:30:41.785Z.json

@@ -1,5 +0,0 @@
-{
-	"stage": 3,
-	"include": false,
-	"config": "./config/default"
-}