node-html-parser 7.0.1 → 7.0.2

package/CHANGELOG.md

@@ -2,6 +2,16 @@
 
 All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
 
+### [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)
 
 

package/README.md

@@ -43,6 +43,7 @@ import { parse } from 'node-html-parser';
 
 const root = parse('<ul id="list"><li>Hello World</li></ul>');
 
+// parse() adds a wrapper node, so the input data's first node is the root's first child node
 console.log(root.firstChild.structure);
 // ul#list
 //   li
@@ -74,7 +75,7 @@ var root = HTMLParser.parse('<ul id="list"><li>Hello World</li></ul>');
 
 ### parse(data[, options])
 
-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.
 
 - **data**, data to parse
 - **options**, parse options
@@ -349,11 +350,11 @@ Get all child elements, so all child nodes of type HTMLELement.
 
 ### firstChild
 
-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.
 
 ### firstElementChild
 

package/dist/main.js

@@ -503,7 +503,7 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
             _this.nodeType = type_3.default.ELEMENT_NODE;
             _this.rawTagName = tagName;
             _this.rawAttrs = rawAttrs || '';
-            _this.id = keyAttrs.id || '';
+            _this._id = keyAttrs.id || '';
             _this.childNodes = [];
             _this._parseOptions = _parseOptions;
             _this.classList = new DOMTokenList(keyAttrs.class ? keyAttrs.class.split(/\s+/) : [], function (classList) { return _this.setAttribute('class', classList.toString()); } // eslint-disable-line @typescript-eslint/no-unsafe-member-access, @typescript-eslint/no-unsafe-call
@@ -590,6 +590,16 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
             enumerable: false,
             configurable: true
         });
+        Object.defineProperty(HTMLElement.prototype, "id", {
+            get: function () {
+                return this._id;
+            },
+            set: function (newid) {
+                this.setAttribute('id', newid);
+            },
+            enumerable: false,
+            configurable: true
+        });
         Object.defineProperty(HTMLElement.prototype, "rawText", {
             /**
              * Get escpaed (as-it) text value of current node and its children.
@@ -786,7 +796,7 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
                     res.push('  '.repeat(indention) + str);
                 }
                 function dfs(node) {
-                    var idStr = node.id ? "#".concat(node.id) : '';
+                    var idStr = node._id ? "#".concat(node._id) : '';
                     var classStr = node.classList.length ? ".".concat(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
                     write("".concat(node.rawTagName).concat(idStr).concat(classStr));
                     indention++;
@@ -923,7 +933,7 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
                     continue;
                 }
                 if (child.nodeType === type_3.default.ELEMENT_NODE) {
-                    if (child.id === id) {
+                    if (child._id === id) {
                         return child;
                     }
                     // if children are existing push the current status to the stack and keep searching for elements in the level below
@@ -1073,9 +1083,9 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
                 return "".concat(name, "=").concat(val);
             })
                 .join(' ');
-            // Update this.id
+            // Update this._id
             if (key === 'id') {
-                this.id = '';
+                this._id = '';
             }
             return this;
         };
@@ -1121,9 +1131,9 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
                 return "".concat(name, "=").concat(val);
             })
                 .join(' ');
-            // Update this.id
+            // Update this._id
             if (key === 'id') {
-                this.id = value;
+                this._id = value;
             }
             return this;
         };
@@ -1150,6 +1160,10 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
                 return "".concat(name, "=").concat(_this.quoteAttribute(String(val)));
             })
                 .join(' ');
+            // Update this._id
+            if ('id' in attributes) {
+                this._id = attributes['id'];
+            }
             return this;
         };
         HTMLElement.prototype.insertAdjacentHTML = function (where, html) {
@@ -1421,6 +1435,9 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
         th: { tr: true, table: true, TR: true, TABLE: true },
         TH: { tr: true, table: true, TR: true, TABLE: true },
     };
+    var kElementsClosedByClosingExcept = {
+        p: { a: true, audio: true, del: true, ins: true, map: true, noscript: true, video: true },
+    };
     var frameflag = 'documentfragmentcontainer';
     /**
      * Parses HTML and returns a root element
@@ -1566,6 +1583,25 @@ define("nodes/html", ["require", "exports", "css-select", "he", "back", "matcher
                                 continue;
                             }
                         }
+                        var openTag = currentParent.rawTagName ?
+                            currentParent.rawTagName.toLowerCase() :
+                            '';
+                        if (kElementsClosedByClosingExcept[openTag]) {
+                            var closingTag = tagName.toLowerCase();
+                            if (stack.length > 1) {
+                                var 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.
                         break;
                     }

package/dist/nodes/html.d.ts

@@ -43,8 +43,8 @@ export default class HTMLElement extends Node {
     private _attrs;
     private _rawAttrs;
     private _parseOptions;
+    private _id;
     rawTagName: string;
-    id: string;
     classList: DOMTokenList;
     /**
      * Node Type declaration.
@@ -79,6 +79,8 @@ export default class HTMLElement extends Node {
     set tagName(newname: string);
     get localName(): string;
     get isVoidElement(): boolean;
+    get id(): string;
+    set id(newid: string);
     /**
      * Get escpaed (as-it) text value of current node and its children.
      * @return {string} text content

package/dist/nodes/html.js

@@ -126,7 +126,7 @@ class HTMLElement extends node_1.default {
         this.nodeType = type_1.default.ELEMENT_NODE;
         this.rawTagName = tagName;
         this.rawAttrs = rawAttrs || '';
-        this.id = keyAttrs.id || '';
+        this._id = keyAttrs.id || '';
         this.childNodes = [];
         this._parseOptions = _parseOptions;
         this.classList = new DOMTokenList(keyAttrs.class ? keyAttrs.class.split(/\s+/) : [], (classList) => this.setAttribute('class', classList.toString()) // eslint-disable-line @typescript-eslint/no-unsafe-member-access, @typescript-eslint/no-unsafe-call
@@ -185,6 +185,12 @@ class HTMLElement extends node_1.default {
     get isVoidElement() {
         return this.voidTag.isVoidElement(this.localName);
     }
+    get id() {
+        return this._id;
+    }
+    set id(newid) {
+        this.setAttribute('id', newid);
+    }
     /**
      * Get escpaed (as-it) text value of current node and its children.
      * @return {string} text content
@@ -350,7 +356,7 @@ class HTMLElement extends node_1.default {
             res.push('  '.repeat(indention) + str);
         }
         function dfs(node) {
-            const idStr = node.id ? `#${node.id}` : '';
+            const idStr = node._id ? `#${node._id}` : '';
             const classStr = node.classList.length ? `.${node.classList.value.join('.')}` : ''; // eslint-disable-line @typescript-eslint/no-unsafe-member-access, @typescript-eslint/no-unsafe-member-access, @typescript-eslint/restrict-template-expressions, @typescript-eslint/no-unsafe-call
             write(`${node.rawTagName}${idStr}${classStr}`);
             indention++;
@@ -483,7 +489,7 @@ class HTMLElement extends node_1.default {
                 continue;
             }
             if (child.nodeType === type_1.default.ELEMENT_NODE) {
-                if (child.id === id) {
+                if (child._id === id) {
                     return child;
                 }
                 // if children are existing push the current status to the stack and keep searching for elements in the level below
@@ -623,9 +629,9 @@ class HTMLElement extends node_1.default {
             return `${name}=${val}`;
         })
             .join(' ');
-        // Update this.id
+        // Update this._id
         if (key === 'id') {
-            this.id = '';
+            this._id = '';
         }
         return this;
     }
@@ -670,9 +676,9 @@ class HTMLElement extends node_1.default {
             return `${name}=${val}`;
         })
             .join(' ');
-        // Update this.id
+        // Update this._id
         if (key === 'id') {
-            this.id = value;
+            this._id = value;
         }
         return this;
     }
@@ -698,6 +704,10 @@ class HTMLElement extends node_1.default {
             return `${name}=${this.quoteAttribute(String(val))}`;
         })
             .join(' ');
+        // Update this._id
+        if ('id' in attributes) {
+            this._id = attributes['id'];
+        }
         return this;
     }
     insertAdjacentHTML(where, html) {
@@ -905,6 +915,9 @@ const kElementsClosedByClosing = {
     th: { tr: true, table: true, TR: true, TABLE: true },
     TH: { tr: true, table: true, TR: true, TABLE: true },
 };
+const kElementsClosedByClosingExcept = {
+    p: { a: true, audio: true, del: true, ins: true, map: true, noscript: true, video: true },
+};
 const frameflag = 'documentfragmentcontainer';
 /**
  * Parses HTML and returns a root element
@@ -1049,6 +1062,25 @@ function base_parse(data, options = {}) {
                             continue;
                         }
                     }
+                    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.
                     break;
                 }

package/package.json

@@ -1,6 +1,6 @@
 {
 	"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.",
 	"main": "dist/index.js",
 	"types": "dist/index.d.ts",
@@ -87,7 +87,8 @@
 		"standard-version": "^9.5.0",
 		"travis-cov": "latest",
 		"ts-node": "^10.9.1",
-		"typescript": "latest"
+		"typescript": "latest",
+		"yarn": "^1.22.22"
 	},
 	"config": {
 		"blanket": {