node-html-parser - npm Package Compare versions

Comparing version 7.0.2 to 7.1.0

CHANGELOG.md

@@ -5,2 +5,15 @@ # Changelog
 
+## [7.1.0](https://github.com/taoqf/node-fast-html-parser/compare/v7.0.2...v7.1.0) (2026-03-03)
+
+
+### Features
+
+* add option closeAllOnClosing ([44c900a](https://github.com/taoqf/node-fast-html-parser/commit/44c900acc01b8923eb9e45c7b13d6bd148a8e9cd)), closes [#294](https://github.com/taoqf/node-fast-html-parser/issues/294)
+* add preserveTagNesting option to maintain invalid HTML nesting [#295](https://github.com/taoqf/node-fast-html-parser/issues/295) ([d604652](https://github.com/taoqf/node-fast-html-parser/commit/d604652cc7c963118ba16ec6bda1f4e01fb81c9e))
+
+
+### Bug Fixes
+
+* add missing dev dependency: yarn ([8679d32](https://github.com/taoqf/node-fast-html-parser/commit/8679d3231e6dc1c93f99921d16b728aa9a578ce5))
+
 ### [7.0.2](https://github.com/taoqf/node-fast-html-parser/compare/v7.0.1...v7.0.2) (2026-01-07)
@@ -7,0 +20,0 @@

dist/nodes/html.d.ts

@@ -136,2 +136,8 @@ import VoidTag from '../void-tag';
     /**
+     * Tests whether the node matches a given CSS selector.
+     * @param  {string}   selector Simplified CSS selector
+     * @return {boolean}
+     */
+    matches(selector: string): boolean;
+    /**
      * find elements by their tagName
@@ -237,2 +243,6 @@ * @param {string} tagName the tagName of the elements to select
     parseNoneClosedTags?: boolean;
+    /**
+     * When true, preserves invalid HTML nesting (e.g., <p><p>bar</p></p>) instead of auto-closing tags
+     */
+    preserveTagNesting?: boolean;
     blockTextElements: {
@@ -251,2 +261,3 @@ [tag: string]: boolean;
     };
+    closeAllByClosing?: boolean;
 }
@@ -253,0 +264,0 @@ /**

dist/nodes/html.js

@@ -431,2 +431,13 @@ "use strict";
     /**
+     * Tests whether the node matches a given CSS selector.
+     * @param  {string}   selector Simplified CSS selector
+     * @return {boolean}
+     */
+    matches(selector) {
+        return (0, css_select_1.is)(this, selector, {
+            xmlMode: true,
+            adapter: matcher_1.default,
+        });
+    }
+    /**
      * find elements by their tagName
@@ -1001,3 +1012,3 @@ * @param {string} tagName the tagName of the elements to select
             const parentTagName = currentParent.rawTagName;
-            if (!closingSlash && kElementsClosedByOpening[parentTagName]) {
+            if (!closingSlash && !options.preserveTagNesting && kElementsClosedByOpening[parentTagName]) {
                 if (kElementsClosedByOpening[parentTagName][tagName]) {
@@ -1086,2 +1097,19 @@ stack.pop();
                     }
+                    if (options.closeAllByClosing === true) {
+                        // If tag was opened, close all nested tags
+                        let i;
+                        for (i = stack.length - 2; i >= 0; i--) {
+                            if (stack[i].rawTagName === tagName)
+                                break;
+                        }
+                        if (i >= 0) {
+                            while (stack.length > i) {
+                                // Update range end for closed tag
+                                currentParent.range[1] = createRange(-1, Math.max(lastTextPos, tagEndPos))[1];
+                                stack.pop();
+                                currentParent = (0, back_1.default)(stack);
+                            }
+                            continue;
+                        }
+                    }
                     // Use aggressive strategy to handle unmatching markups.
@@ -1088,0 +1116,0 @@ break;

package.json

 {
 	"name": "node-html-parser",
-	"version": "7.0.2",
+	"version": "7.1.0",
 	"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

@@ -89,2 +89,3 @@ # 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)
     parseNoneClosedTags: false, 	// close none closed HTML tags instead of removing them 
+    preserveTagNesting: false,		// preserve invalid HTML nesting instead of auto-closing tags (e.g. <p><p>bar</p></p>)
     voidTag: {
@@ -99,3 +100,4 @@ tags: ['area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', 'track', 'wbr'],	// optional and case insensitive, default value is ['area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', 'track', 'wbr']
       pre: true			// keep text content when parsing
-    }
+    },
+    closeAllOnClosing: false  // Close all non-closed tags when containing element closes
   }
@@ -118,2 +120,3 @@ ```
 	Node querySelector(string selector)
+	boolean matches(string selector)
 	HTMLElement[] getElementsByTagName(string tagName)
@@ -213,2 +216,6 @@ Node closest(string selector)
 
+### matches(selector)
+
+Tests whether the node matches a given CSS selector.
+
 ### getElementsByTagName(tagName)
@@ -215,0 +222,0 @@

New alerts

Long strings

Supply chain risk

Contains long string literals, which may be a sign of obfuscated or packed code.

Found 1 instance in 1 package

Fixed alerts

Long strings

Supply chain risk

Contains long string literals, which may be a sign of obfuscated or packed code.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

172579

2.39%

Lines of code

3781

1.8%

Number of lines in readme file

413

1.72%

No dependency changes