node-html-parser - npm Package Compare versions

Comparing version 8.0.1 to 8.0.2

CHANGELOG.md

@@ -5,2 +5,10 @@ # Changelog
 
+### [8.0.2](https://github.com/taoqf/node-fast-html-parser/compare/v8.0.1...v8.0.2) (2026-06-21)
+
+
+### Bug Fixes
+
+* preserve backslashes in attribute values during serialization and round-trip parsing [#306](https://github.com/taoqf/node-fast-html-parser/issues/306) ([a9882b2](https://github.com/taoqf/node-fast-html-parser/commit/a9882b245d2a1e1adfe6b3a61d6f3fa3bfbb3e32))
+* update casing of HTML tag names in usage example [#289](https://github.com/taoqf/node-fast-html-parser/issues/289) ([801d278](https://github.com/taoqf/node-fast-html-parser/commit/801d278d6b23c99b196461590dbbf3f60339a22d))
+
 ### [8.0.1](https://github.com/taoqf/node-fast-html-parser/compare/v8.0.0...v8.0.1) (2026-06-20)
@@ -7,0 +15,0 @@

dist/nodes/html.js

@@ -106,6 +106,6 @@ "use strict";
         return JSON.stringify(attr.replace(/"/g, '"'))
-            .replace(/\\t/g, '\t')
-            .replace(/\\n/g, '\n')
-            .replace(/\\r/g, '\r')
-            .replace(/\\/g, '');
+            .replace(/([^\\])\\t/g, '$1\t')
+            .replace(/([^\\])\\n/g, '$1\n')
+            .replace(/([^\\])\\r/g, '$1\r')
+            .replace(/([^\\])\\/g, '$1');
     }
@@ -887,2 +887,3 @@ /**
 const kMarkupPattern = /<!--[\s\S]*?-->|<(\/?)([a-zA-Z][-.:0-9_a-zA-Z@\xB7\xC0-\xD6\xD8-\xF6\u00F8-\u03A1\u03A3-\u03D9\u03DB-\u03EF\u03F7-\u03FF\u0400-\u04FF\u0500-\u052F\u1D00-\u1D2B\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1E9B\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u2132\u214E\u2160-\u2188\u2C60-\u2C7F\uA722-\uA787\uA78B-\uA78E\uA790-\uA7AD\uA7B0-\uA7B7\uA7F7-\uA7FF\uAB30-\uAB5A\uAB5C-\uAB5F\uAB64-\uAB65\uFB00-\uFB06\uFB13-\uFB17\uFF21-\uFF3A\uFF41-\uFF5A\x37F-\u1FFF\u200C-\u200D\u203F-\u2040\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD]*)((?:\s+[^>]*?(?:(?:'[^']*')|(?:"[^"]*"))?)*)\s*(\/?)>/gu;
+const kMarkupPatternWithCDATA = /<!--[\s\S]*?-->|<!\[CDATA\[[\s\S]*?\]\]>|<(\/?)([a-zA-Z][-.:0-9_a-zA-Z@\xB7\xC0-\xD6\xD8-\xF6\u00F8-\u03A1\u03A3-\u03D9\u03DB-\u03EF\u03F7-\u03FF\u0400-\u04FF\u0500-\u052F\u1D00-\u1D2B\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1E9B\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u2132\u214E\u2160-\u2188\u2C60-\u2C7F\uA722-\uA787\uA78B-\uA78E\uA790-\uA7AD\uA7B0-\uA7B7\uA7F7-\uA7FF\uAB30-\uAB5A\uAB5C-\uAB5F\uAB64-\uAB65\uFB00-\uFB06\uFB13-\uFB17\uFF21-\uFF3A\uFF41-\uFF5A\x37F-\u1FFF\u200C-\u200D\u203F-\u2040\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD]*)((?:\s+[^>]*?(?:(?:'[^']*')|(?:"[^"]*"))?)*)\s*(\/?)>/gu;
 // const kMarkupPattern = /<!--[\s\S]*?-->|<(\/?)([a-zA-Z][-.:0-9_a-zA-Z]*)((?:\s+[^>]*?(?:(?:'[^']*')|(?:"[^"]*"))?)*)\s*(\/?)>/g;
@@ -943,2 +944,4 @@ const kAttributePattern = /(?:^|\s)(id|class)\s*=\s*((?:'[^']*')|(?:"[^"]*")|\S+)/gi;
     const voidTag = new void_tag_1.default((_a = options === null || options === void 0 ? void 0 : options.voidTag) === null || _a === void 0 ? void 0 : _a.closingSlash, (_b = options === null || options === void 0 ? void 0 : options.voidTag) === null || _b === void 0 ? void 0 : _b.tags);
+    const hasCDATA = data.includes('<![CDATA[');
+    const markupPattern = hasCDATA ? kMarkupPatternWithCDATA : kMarkupPattern;
     const elements = options.blockTextElements || {
@@ -971,3 +974,4 @@ script: true,
     const frameFlagOffset = frameflag.length + 2;
-    while ((match = kMarkupPattern.exec(data))) {
+    markupPattern.lastIndex = 0;
+    while ((match = markupPattern.exec(data))) {
         // Note: Object destructuring here consistently tests as higher performance than array destructuring
@@ -977,4 +981,4 @@ // eslint-disable-next-line prefer-const
         const matchLength = matchText.length;
-        const tagStartPos = kMarkupPattern.lastIndex - matchLength;
-        const tagEndPos = kMarkupPattern.lastIndex;
+        const tagStartPos = markupPattern.lastIndex - matchLength;
+        const tagEndPos = markupPattern.lastIndex;
         // Add TextNode if content
@@ -987,3 +991,7 @@ if (lastTextPos > -1) {
         }
-        lastTextPos = kMarkupPattern.lastIndex;
+        lastTextPos = markupPattern.lastIndex;
+        if (hasCDATA && matchText.startsWith('<![CDATA[')) {
+            currentParent.appendChild(new text_1.default(matchText, currentParent, createRange(tagStartPos, tagEndPos)));
+            continue;
+        }
         // https://github.com/taoqf/node-html-parser/issues/38
@@ -1030,3 +1038,3 @@ // Skip frameflag node
             }
-            const tagEndPos = kMarkupPattern.lastIndex;
+            const tagEndPos = markupPattern.lastIndex;
             const tagStartPos = tagEndPos - matchLength;
@@ -1041,4 +1049,4 @@ currentParent = currentParent.appendChild(
                 const closeIndex = lowerCaseTagName
-                    ? data.toLocaleLowerCase().indexOf(closeMarkup, kMarkupPattern.lastIndex)
-                    : data.indexOf(closeMarkup, kMarkupPattern.lastIndex);
+                    ? data.toLocaleLowerCase().indexOf(closeMarkup, markupPattern.lastIndex)
+                    : data.indexOf(closeMarkup, markupPattern.lastIndex);
                 const textEndPos = closeIndex === -1 ? dataEndPos : closeIndex;
@@ -1052,6 +1060,6 @@ if (element_should_be_ignore(tagName)) {
                 if (closeIndex === -1) {
-                    lastTextPos = kMarkupPattern.lastIndex = data.length + 1;
+                    lastTextPos = markupPattern.lastIndex = data.length + 1;
                 }
                 else {
-                    lastTextPos = kMarkupPattern.lastIndex = closeIndex + closeMarkup.length;
+                    lastTextPos = markupPattern.lastIndex = closeIndex + closeMarkup.length;
                     // Cause to be treated as self-closing, because no close found
@@ -1058,0 +1066,0 @@ leadingSlash = '/';

package.json

 {
 	"name": "node-html-parser",
-	"version": "8.0.1",
+	"version": "8.0.2",
 	"description": "A very fast HTML parser, generating a simplified DOM, with basic element query support.",
@@ -5,0 +5,0 @@ "main": "dist/index.js",

README.md

@@ -53,6 +53,6 @@ # Fast HTML Parser [![NPM version](https://badge.fury.io/js/node-html-parser.png)](http://badge.fury.io/js/node-html-parser) [![Build Status](https://img.shields.io/endpoint.svg?url=https%3A%2F%2Factions-badge.atrox.dev%2Ftaoqf%2Fnode-html-parser%2Fbadge%3Fref%3Dmain&style=flat)](https://actions-badge.atrox.dev/taoqf/node-html-parser/goto?ref=main)
 console.log(root.querySelector('#list'));
-// { tagName: 'ul',
+// { tagName: 'UL',
 //   rawAttrs: 'id="list"',
 //   childNodes:
-//    [ { tagName: 'li',
+//    [ { tagName: 'LI',
 //        rawAttrs: '',
@@ -59,0 +59,0 @@ //        childNodes: [Object],

No alert changes

Improved metrics

Total package byte prevSize

176479

1.81%

Lines of code

3801

0.58%

No dependency changes