node-html-parser - npm Package Compare versions

Comparing version 7.0.1 to 7.0.2

CHANGELOG.md

@@ -5,2 +5,12 @@ # Changelog
 
+### [7.0.2](https://github.com/taoqf/node-fast-html-parser/compare/v7.0.1...v7.0.2) (2026-01-07)
+
+
+### Bug Fixes
+
+* [#227](https://github.com/taoqf/node-fast-html-parser/issues/227) ([51528c4](https://github.com/taoqf/node-fast-html-parser/commit/51528c41ef2648d6c4dc1aecd14ee9d2b0083c4f))
+* [#294](https://github.com/taoqf/node-fast-html-parser/issues/294) Closing tag is missing but valid HTML is still not parseable ([950865f](https://github.com/taoqf/node-fast-html-parser/commit/950865fab5f4df7853b36712869b71c90f4d3a1b))
+* add missing dev dependency: yarn ([6d73ea3](https://github.com/taoqf/node-fast-html-parser/commit/6d73ea37c48f4170c35907869ba410c5122a9a1f))
+* test valid.js ([a81fc46](https://github.com/taoqf/node-fast-html-parser/commit/a81fc46fab2507615b0362150d62568a6f52ee4e))
+
 ### [7.0.1](https://github.com/taoqf/node-fast-html-parser/compare/v7.0.0...v7.0.1) (2024-12-26)
@@ -7,0 +17,0 @@

dist/nodes/html.d.ts

@@ -46,4 +46,4 @@ import VoidTag from '../void-tag';
     private _parseOptions;
+    private _id;
     rawTagName: string;
-    id: string;
     classList: DOMTokenList;
@@ -83,2 +83,4 @@ /**
     get isVoidElement(): boolean;
+    get id(): string;
+    set id(newid: string);
     /**
@@ -85,0 +87,0 @@ * Get escpaed (as-it) text value of current node and its children.

dist/nodes/html.js

@@ -129,3 +129,3 @@ "use strict";
         this.rawAttrs = rawAttrs || '';
-        this.id = keyAttrs.id || '';
+        this._id = keyAttrs.id || '';
         this.childNodes = [];
@@ -189,2 +189,8 @@ this._parseOptions = _parseOptions;
     }
+    get id() {
+        return this._id;
+    }
+    set id(newid) {
+        this.setAttribute('id', newid);
+    }
     /**
@@ -355,3 +361,3 @@ * Get escpaed (as-it) text value of current node and its children.
         function dfs(node) {
-            const idStr = node.id ? `#${node.id}` : '';
+            const idStr = node._id ? `#${node._id}` : '';
             const classStr = node.classList.length ? `.${node.classList.value.join('.')}` : ''; // eslint-disable-line @typescript-eslint/no-unsafe-member-access, @typescript-eslint/no-unsafe-member-access, @typescript-eslint/restrict-template-expressions, @typescript-eslint/no-unsafe-call
@@ -489,3 +495,3 @@ write(`${node.rawTagName}${idStr}${classStr}`);
             if (child.nodeType === type_1.default.ELEMENT_NODE) {
-                if (child.id === id) {
+                if (child._id === id) {
                     return child;
@@ -630,5 +636,5 @@ }
             .join(' ');
-        // Update this.id
+        // Update this._id
         if (key === 'id') {
-            this.id = '';
+            this._id = '';
         }
@@ -678,5 +684,5 @@ return this;
             .join(' ');
-        // Update this.id
+        // Update this._id
         if (key === 'id') {
-            this.id = value;
+            this._id = value;
         }
@@ -707,2 +713,6 @@ return this;
             .join(' ');
+        // Update this._id
+        if ('id' in attributes) {
+            this._id = attributes['id'];
+        }
         return this;
@@ -915,2 +925,5 @@ }
 };
+const kElementsClosedByClosingExcept = {
+    p: { a: true, audio: true, del: true, ins: true, map: true, noscript: true, video: true },
+};
 const frameflag = 'documentfragmentcontainer';
@@ -1060,2 +1073,21 @@ /**
                     }
+                    const openTag = currentParent.rawTagName ?
+                        currentParent.rawTagName.toLowerCase() :
+                        '';
+                    if (kElementsClosedByClosingExcept[openTag]) {
+                        const closingTag = tagName.toLowerCase();
+                        if (stack.length > 1) {
+                            const possibleContainer = stack[stack.length - 2];
+                            if (possibleContainer &&
+                                possibleContainer.rawTagName &&
+                                possibleContainer.rawTagName.toLowerCase() === closingTag &&
+                                !kElementsClosedByClosingExcept[openTag][closingTag]) {
+                                // 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.
@@ -1062,0 +1094,0 @@ break;

package.json

 {
 	"name": "node-html-parser",
-	"version": "7.0.1",
+	"version": "7.0.2",
 	"description": "A very fast HTML parser, generating a simplified DOM, with basic element query support.",
@@ -90,3 +90,4 @@ "main": "dist/index.js",
 		"ts-node": "^10.9.1",
-		"typescript": "latest"
+		"typescript": "latest",
+		"yarn": "^1.22.22"
 	},
@@ -93,0 +94,0 @@ "config": {

README.md

@@ -46,2 +46,3 @@ # 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)
 
+// parse() adds a wrapper node, so the input data's first node is the root's first child node
 console.log(root.firstChild.structure);
@@ -78,3 +79,3 @@ // ul#list
 
-Parse the data provided, and return the root of the generated DOM.
+Parse the data provided, wrap the result in a new node, and return the root of the generated DOM.
 
@@ -354,7 +355,7 @@ - **data**, data to parse
 
-Get first child node. `undefined` if the node has no children.
+Get first child node of the wrapper node added by `parse()`. `undefined` if the node has no children.
 
 ### lastChild
 
-Get last child node. `undefined` if the node has no children.
+Get last child node of the wrapper node added by `parse()`. `undefined` if the node has no children.
 
@@ -361,0 +362,0 @@ ### firstElementChild

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

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

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

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

168552

2.66%

Lines of code

3714

1.92%

Number of lines in readme file

406

0.25%

Worsened metrics

Dev dependency count

35

2.94%

No dependency changes