fast-xml-parser 4.5.1 → 4.5.3

package/CHANGELOG.md

@@ -1,5 +1,10 @@
 <small>Note: If you find missing information about particular minor version, that version must have been changed without any functional change in this library.</small>
 
+**4.5.2 / 2025-02-18**
+- Fix null CDATA to comply with undefined behavior (#701) (By [Matthieu BOHEAS](https://github.com/Kelgors))
+- Fix(performance): Update check for leaf node in saveTextToParentTag function in OrderedObjParser.js (#707) (By [...](https://github.com/tomingtoming))
+- Fix: emit full JSON string from CLI when no output filename specified (#710) (By [Matt Benson](https://github.com/mbenson))
+
 **4.5.1 / 2024-12-15**
 - Fix empty tag key name for v5 (#697).  no impact on v4
 - Fixes entity parsing when used in strict mode (#699)

package/README.md

@@ -9,8 +9,7 @@ Validate XML, Parse XML to JS Object, or Build XML from JS Object without C/C++
 
 ---
 
-<a href="https://www.amazon.in/Power-Glasses-world-imagination-Perspective-ebook/dp/B0CW1CJGNK/"><img align="left" src="https://github.com/NaturalIntelligence/fast-xml-parser/assets/7692328/e7a42bcc-5186-45e3-bfee-de8d8b9a69d4" alt="ads-thePowerGlassesBook"/></a>
-I had recently published a book, The Power Glasses. Please have a look. Your feedback would be helpful. You can [mail](githubissues@proton.me) me for a free copy.
+<small>Checkout our new library [Text2Chart](https://solothought.com/text2chart/flow) that constructs flow chart out of simple text. Very helpful in creating or alayzing an algorithm, and documentation purpose</small>
 <br>
 
 Sponsor this project
@@ -51,8 +50,9 @@ Through OpenCollective
 -->
 
 ![fxp_sponsors](https://raw.githubusercontent.com/NaturalIntelligence/ThankYouBackers/main/assets/NI_sponsors.jpg)
-<a href="https://github.com/cocopon" target="_blank">Hiroki Kokubun</a>
+- <a href="https://github.com/cocopon" target="_blank">Hiroki Kokubun</a>
 
+> This is a donation. No goods or services are expected in return. Any requests for refunds for those purposes will be rejected.
 ## Users
 
 <a href="https://github.com/renovatebot/renovate" title="renovate" ><img src="https://avatars1.githubusercontent.com/u/38656520" width="60px" ></a>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fast-xml-parser",
-  "version": "4.5.1",
+  "version": "4.5.3",
   "description": "Validate XML, Parse XML, Build XML without C/C++ based libraries",
   "main": "./src/fxp.js",
   "scripts": {
@@ -60,14 +60,13 @@
     "webpack-cli": "^4.9.1"
   },
   "typings": "src/fxp.d.ts",
-  "funding": [{
-    "type": "github",
-    "url": "https://github.com/sponsors/NaturalIntelligence"
-  },{
-    "type": "paypal",
-    "url": "https://paypal.me/naturalintelligence"
-  }],
+  "funding": [
+    {
+      "type": "github",
+      "url": "https://github.com/sponsors/NaturalIntelligence"
+    }
+  ],
   "dependencies": {
-    "strnum": "^1.0.5"
+    "strnum": "^1.1.1"
   }
 }

package/src/cli/cli.js

@@ -57,7 +57,7 @@ if (process.argv[2] === '--help' || process.argv[2] === '-h') {
     if (outputFileName) {
       writeToFile(outputFileName, output);
     } else {
-      console.log(output);
+      console.log(JSON.stringify(output, null, 2));
     }
   };
 

package/src/v6/CharsSymbol.js

@@ -0,0 +1,16 @@
+export default {
+  "<" : "<", //tag start
+  ">" : ">", //tag end
+  "/" : "/", //close tag
+  "!" : "!", //comment or docttype
+  "!--" : "!--", //comment
+  "-->" : "-->", //comment end
+  "?" : "?", //pi
+  "?>" : "?>", //pi end
+  "?xml" : "?xml", //pi end
+  "![" : "![", //cdata
+  "]]>" : "]]>", //cdata end
+  "[" : "[",
+  "-" : "-",
+  "D" : "D",
+}

package/src/v6/EntitiesParser.js

@@ -0,0 +1,104 @@
+const ampEntity = { regex: /&(amp|#38|#x26);/g, val : "&"};
+const htmlEntities = {
+    "space": { regex: /&(nbsp|#160);/g, val: " " },
+    // "lt" : { regex: /&(lt|#60);/g, val: "<" },
+    // "gt" : { regex: /&(gt|#62);/g, val: ">" },
+    // "amp" : { regex: /&(amp|#38);/g, val: "&" },
+    // "quot" : { regex: /&(quot|#34);/g, val: "\"" },
+    // "apos" : { regex: /&(apos|#39);/g, val: "'" },
+    "cent" : { regex: /&(cent|#162);/g, val: "¢" },
+    "pound" : { regex: /&(pound|#163);/g, val: "£" },
+    "yen" : { regex: /&(yen|#165);/g, val: "¥" },
+    "euro" : { regex: /&(euro|#8364);/g, val: "€" },
+    "copyright" : { regex: /&(copy|#169);/g, val: "©" },
+    "reg" : { regex: /&(reg|#174);/g, val: "®" },
+    "inr" : { regex: /&(inr|#8377);/g, val: "₹" },
+    "num_dec": { regex: /&#([0-9]{1,7});/g, val : (_, str) => String.fromCharCode(Number.parseInt(str, 10)) },
+    "num_hex": { regex: /&#x([0-9a-fA-F]{1,6});/g, val : (_, str) => String.fromCharCode(Number.parseInt(str, 16)) },
+};
+export default class EntitiesParser{
+    constructor(replaceHtmlEntities) {
+      this.replaceHtmlEntities = replaceHtmlEntities;
+      this.docTypeEntities = {};
+      this.lastEntities = {
+        "apos" : { regex: /&(apos|#39|#x27);/g, val : "'"},
+        "gt" : { regex: /&(gt|#62|#x3E);/g, val : ">"},
+        "lt" : { regex: /&(lt|#60|#x3C);/g, val : "<"},
+        "quot" : { regex: /&(quot|#34|#x22);/g, val : "\""},
+      };
+    }
+
+    addExternalEntities(externalEntities){
+        const entKeys = Object.keys(externalEntities);
+        for (let i = 0; i < entKeys.length; i++) {
+          const ent = entKeys[i];
+          this.addExternalEntity(ent,externalEntities[ent])
+        }
+    }
+    addExternalEntity(key,val){
+      validateEntityName(key);
+      if(val.indexOf("&") !== -1) {
+        reportWarning(`Entity ${key} is not added as '&' is found in value;`)
+        return;
+      }else{
+        this.lastEntities[ent] = {
+          regex: new RegExp("&"+key+";","g"),
+          val : val
+        }
+      }
+    }
+
+    addDocTypeEntities(entities){
+        const entKeys = Object.keys(entities);
+        for (let i = 0; i < entKeys.length; i++) {
+          const ent = entKeys[i];
+          this.docTypeEntities[ent] = {
+             regex: new RegExp("&"+ent+";","g"),
+             val : entities[ent]
+          }
+        }
+    }
+
+    parse(val){
+        return this.replaceEntitiesValue(val)
+    }
+
+    /**
+     * 1. Replace DOCTYPE entities 
+     * 2. Replace external entities 
+     * 3. Replace HTML entities if asked
+     * @param {string} val 
+     */
+    replaceEntitiesValue(val){
+        if(typeof val === "string" && val.length > 0){
+            for(let entityName in this.docTypeEntities){
+                const entity = this.docTypeEntities[entityName];
+                val = val.replace( entity.regx, entity.val);
+              }
+              for(let entityName in this.lastEntities){
+                const entity = this.lastEntities[entityName];
+                val = val.replace( entity.regex, entity.val);
+              }
+              if(this.replaceHtmlEntities){
+                for(let entityName in htmlEntities){
+                  const entity = htmlEntities[entityName];
+                  val = val.replace( entity.regex, entity.val);
+                }
+              }
+            val = val.replace( ampEntity.regex, ampEntity.val);
+        }
+        return val;
+    }
+};
+
+//an entity name should not contains special characters that may be used in regex
+//Eg !?\\\/[]$%{}^&*()<>
+const specialChar = "!?\\\/[]$%{}^&*()<>|+";
+
+function validateEntityName(name){
+    for (let i = 0; i < specialChar.length; i++) {
+        const ch = specialChar[i];
+        if(name.indexOf(ch) !== -1) throw new Error(`Invalid character ${ch} in entity name`);
+    }
+    return name;
+}

package/src/v6/OptionsBuilder.js

@@ -0,0 +1,61 @@
+
+import {JsObjOutputBuilder} from './OutputBuilders/JsObjBuilder.js';
+
+export const defaultOptions = {
+  preserveOrder: false,
+  removeNSPrefix: false, // remove NS from tag name or attribute name if true
+  //ignoreRootElement : false,
+  stopNodes: [], //nested tags will not be parsed even for errors
+  // isArray: () => false, //User will set it
+  htmlEntities: false,
+  // skipEmptyListItem: false
+  tags:{
+    unpaired: [],
+    nameFor:{
+      cdata: false,
+      comment: false,
+      text: '#text'
+    },
+    separateTextProperty: false,
+  },
+  attributes:{
+    ignore: false,
+    booleanType: true,
+    entities: true,
+  },
+
+  // select: ["img[src]"],
+  // stop: ["anim", "[ads]"]
+  only: [], // rest tags will be skipped. It will result in flat array
+  hierarchy: false, //will be used when a particular tag is set to be parsed.
+  skip: [], // will be skipped from parse result. on('skip') will be triggered
+
+  select: [], // on('select', tag => tag ) will be called if match
+  stop: [], //given tagPath will not be parsed. innerXML will be set as string value
+  OutputBuilder: new JsObjOutputBuilder(),
+};
+   
+export const buildOptions = function(options) {
+  const finalOptions = { ... defaultOptions};
+  copyProperties(finalOptions,options)
+  return finalOptions;
+};
+
+function copyProperties(target, source) {
+  for (let key in source) {
+    if (source.hasOwnProperty(key)) {
+      if (key === 'OutputBuilder') {
+        target[key] = source[key];
+      }else if (typeof source[key] === 'object' && !Array.isArray(source[key])) {
+        // Recursively copy nested properties
+        if (typeof target[key] === 'undefined') {
+          target[key] = {};
+        }
+        copyProperties(target[key], source[key]);
+      } else {
+        // Copy non-nested properties
+        target[key] = source[key];
+      }
+    }
+  }
+}

package/src/v6/OutputBuilders/BaseOutputBuilder.js

@@ -0,0 +1,69 @@
+export default class BaseOutputBuilder{
+  constructor(){
+    // this.attributes = {};
+  }
+
+  addAttribute(name, value){
+    if(this.options.onAttribute){
+      //TODO: better to pass tag path
+      const v = this.options.onAttribute(name, value, this.tagName);
+      if(v) this.attributes[v.name] = v.value;
+    }else{
+      name = this.options.attributes.prefix + name + this.options.attributes.suffix;
+      this.attributes[name] = this.parseValue(value, this.options.attributes.valueParsers);
+    }
+  }
+
+  /**
+   * parse value by chain of parsers
+   * @param {string} val 
+   * @returns {any} parsed value if matching parser found
+   */
+    parseValue = function(val, valParsers){
+      for (let i = 0; i < valParsers.length; i++) {
+        let valParser = valParsers[i];
+        if(typeof valParser === "string"){
+          valParser = this.registeredParsers[valParser];
+        }
+        if(valParser){
+          val = valParser.parse(val);
+        }
+      }
+      return val;
+    }
+
+  /**
+   * To add a nested empty tag.
+   * @param {string} key 
+   * @param {any} val 
+   */
+  _addChild(key, val){}
+
+  /**
+   * skip the comment if property is not set
+   */
+  addComment(text){
+    if(this.options.nameFor.comment)
+      this._addChild(this.options.nameFor.comment, text);
+  }
+
+  //store CDATA separately if property is set
+  //otherwise add to tag's value
+  addCdata(text){
+    if (this.options.nameFor.cdata) {
+      this._addChild(this.options.nameFor.cdata, text);
+    } else {
+      this.addRawValue(text || "");
+    }
+  }
+
+  addRawValue = text => this.addValue(text);
+
+  addDeclaration(){
+    if(!this.options.declaration){
+    }else{
+      this.addPi("?xml");
+    }
+    this.attributes = {}
+  }
+}

package/src/v6/OutputBuilders/JsArrBuilder.js

@@ -0,0 +1,103 @@
+import {buildOptions,registerCommonValueParsers} from './ParserOptionsBuilder.js';
+
+export default class OutputBuilder{
+  constructor(options){
+    this.options = buildOptions(options);
+      this.registeredParsers = registerCommonValueParsers(this.options);
+    }
+    
+    registerValueParser(name,parserInstance){//existing name will override the parser without warning
+      this.registeredParsers[name] = parserInstance;
+    }
+
+  getInstance(parserOptions){
+    return new JsArrBuilder(parserOptions, this.options, this.registeredParsers);
+  }
+}
+
+const rootName = '!js_arr';
+import BaseOutputBuilder from './BaseOutputBuilder.js';
+
+class JsArrBuilder extends BaseOutputBuilder{
+
+  constructor(parserOptions, options,registeredParsers) {
+    super();
+    this.tagsStack = [];
+    this.parserOptions = parserOptions;
+    this.options = options;
+    this.registeredParsers = registeredParsers;
+
+    this.root = new Node(rootName);
+    this.currentNode = this.root;
+    this.attributes = {};
+  }
+
+  addTag(tag){
+    //when a new tag is added, it should be added as child of current node
+    //TODO: shift this check to the parser
+    if(tag.name === "__proto__") tag.name = "#__proto__";
+
+    this.tagsStack.push(this.currentNode);
+    this.currentNode = new Node(tag.name, this.attributes);
+    this.attributes = {};
+  }
+
+  /**
+   * Check if the node should be added by checking user's preference
+   * @param {Node} node 
+   * @returns boolean: true if the node should not be added
+   */
+  closeTag(){
+    const node = this.currentNode;
+    this.currentNode = this.tagsStack.pop(); //set parent node in scope
+    if(this.options.onClose !== undefined){
+      //TODO TagPathMatcher 
+      const resultTag = this.options.onClose(node, 
+        new TagPathMatcher(this.tagsStack,node));
+
+      if(resultTag) return;
+    }
+    this.currentNode.child.push(node);  //to parent node
+  }
+
+  //Called by parent class methods
+  _addChild(key, val){
+    // if(key === "__proto__") tagName = "#__proto__";
+    this.currentNode.child.push( {[key]: val });
+    // this.currentNode.leafType = false;
+  }
+
+  /**
+   * Add text value child node 
+   * @param {string} text 
+   */
+  addValue(text){
+    this.currentNode.child.push( {[this.options.nameFor.text]: this.parseValue(text, this.options.tags.valueParsers) });
+  }
+
+  addPi(name){
+    //TODO: set pi flag
+    if(!this.options.ignorePiTags){
+      const node = new Node(name, this.attributes);
+      this.currentNode[":@"] = this.attributes;
+      this.currentNode.child.push(node);
+    }
+    this.attributes = {};
+  }
+  getOutput(){
+    return this.root.child[0];
+  }
+}
+
+
+
+class Node{
+  constructor(tagname, attributes){
+    this.tagname = tagname;
+    this.child = []; //nested tags, text, cdata, comments
+    if(attributes && Object.keys(attributes).length > 0)
+      this[":@"] = attributes;
+  }
+}
+
+module.exports = OutputBuilder;

package/src/v6/OutputBuilders/JsMinArrBuilder.js

@@ -0,0 +1,100 @@
+import {buildOptions,registerCommonValueParsers} from"./ParserOptionsBuilder";
+
+export default class OutputBuilder{
+  constructor(options){
+    this.options = buildOptions(options);
+      this.registeredParsers = registerCommonValueParsers(this.options);
+    }
+    
+    registerValueParser(name,parserInstance){//existing name will override the parser without warning
+      this.registeredParsers[name] = parserInstance;
+    }
+
+  getInstance(parserOptions){
+    return new JsMinArrBuilder(parserOptions, this.options, this.registeredParsers);
+  }
+}
+
+import BaseOutputBuilder  from "./BaseOutputBuilder.js";
+const rootName = '^';
+
+class JsMinArrBuilder extends BaseOutputBuilder{
+
+  constructor(parserOptions, options,registeredParsers) {
+    super();
+    this.tagsStack = [];
+    this.parserOptions = parserOptions;
+    this.options = options;
+    this.registeredParsers = registeredParsers;
+
+    this.root = {[rootName]: []};
+    this.currentNode = this.root;
+    this.currentNodeTagName = rootName;
+    this.attributes = {};
+  }
+
+  addTag(tag){
+    //when a new tag is added, it should be added as child of current node
+    //TODO: shift this check to the parser
+    if(tag.name === "__proto__") tag.name = "#__proto__";
+
+    this.tagsStack.push([this.currentNodeTagName,this.currentNode]); //this.currentNode is parent node here
+    this.currentNodeTagName = tag.name;
+    this.currentNode = { [tag.name]:[]}
+    if(Object.keys(this.attributes).length > 0){
+      this.currentNode[":@"] = this.attributes;
+      this.attributes = {};
+    }
+  }
+
+  /**
+   * Check if the node should be added by checking user's preference
+   * @param {Node} node 
+   * @returns boolean: true if the node should not be added
+   */
+  closeTag(){
+    const node = this.currentNode;
+    const nodeName = this.currentNodeTagName;
+    const arr = this.tagsStack.pop(); //set parent node in scope
+    this.currentNodeTagName = arr[0];
+    this.currentNode = arr[1];
+
+    if(this.options.onClose !== undefined){
+      //TODO TagPathMatcher 
+      const resultTag = this.options.onClose(node, 
+        new TagPathMatcher(this.tagsStack,node));
+
+      if(resultTag) return;
+    }
+    this.currentNode[this.currentNodeTagName].push(node);  //to parent node
+  }
+
+  //Called by parent class methods
+  _addChild(key, val){
+    // if(key === "__proto__") tagName = "#__proto__";
+    this.currentNode.push( {[key]: val });
+    // this.currentNode.leafType = false;
+  }
+
+  /**
+   * Add text value child node 
+   * @param {string} text 
+   */
+  addValue(text){
+    this.currentNode[this.currentNodeTagName].push( {[this.options.nameFor.text]: this.parseValue(text, this.options.tags.valueParsers) });
+  }
+
+  addPi(name){
+    if(!this.options.ignorePiTags){
+      const node = { [name]:[]}
+      if(this.attributes){
+        node[":@"] = this.attributes;
+      }
+      this.currentNode.push(node);
+    }
+    this.attributes = {};
+  }
+  getOutput(){
+    return this.root[rootName];
+  }
+}

package/src/v6/OutputBuilders/JsObjBuilder.js

@@ -0,0 +1,154 @@
+
+
+import {buildOptions,registerCommonValueParsers} from './ParserOptionsBuilder.js';
+
+export default class OutputBuilder{
+  constructor(builderOptions){
+      this.options = buildOptions(builderOptions);
+      this.registeredParsers = registerCommonValueParsers(this.options);
+  }
+
+  registerValueParser(name,parserInstance){//existing name will override the parser without warning
+    this.registeredParsers[name] = parserInstance;
+  }
+
+  getInstance(parserOptions){
+    return new JsObjBuilder(parserOptions, this.options, this.registeredParsers);
+  }
+}
+
+import BaseOutputBuilder from './BaseOutputBuilder.js';
+const rootName = '^';
+
+class JsObjBuilder extends BaseOutputBuilder{
+
+  constructor(parserOptions, builderOptions,registeredParsers) {
+    super();
+    //hold the raw detail of a tag and sequence with reference to the output
+    this.tagsStack = [];
+    this.parserOptions = parserOptions;
+    this.options = builderOptions;
+    this.registeredParsers = registeredParsers;
+
+    this.root = {};
+    this.parent = this.root;
+    this.tagName = rootName;
+    this.value = {};
+    this.textValue = "";
+    this.attributes = {};
+  }
+
+  addTag(tag){
+
+    let value = "";
+    if( !isEmpty(this.attributes)){
+      value = {};
+      if(this.options.attributes.groupBy){
+        value[this.options.attributes.groupBy] = this.attributes;
+      }else{
+        value = this.attributes;
+      }
+    }
+
+    this.tagsStack.push([this.tagName, this.textValue, this.value]); //parent tag, parent text value, parent tag value (jsobj)
+    this.tagName = tag.name;
+    this.value = value;
+    this.textValue = "";
+    this.attributes = {};
+  }
+
+  /**
+   * Check if the node should be added by checking user's preference
+   * @param {Node} node 
+   * @returns boolean: true if the node should not be added
+   */
+  closeTag(){
+    const tagName = this.tagName;
+    let value = this.value;
+    let textValue = this.textValue;
+
+    //update tag text value
+    if(typeof value !== "object" && !Array.isArray(value)){
+      value = this.parseValue(textValue.trim(), this.options.tags.valueParsers);
+    }else if(textValue.length > 0){
+      value[this.options.nameFor.text] = this.parseValue(textValue.trim(), this.options.tags.valueParsers);
+    }
+
+    
+    let resultTag= {
+      tagName: tagName,
+      value: value
+    };
+
+    if(this.options.onTagClose !== undefined){
+      //TODO TagPathMatcher 
+      resultTag = this.options.onClose(tagName, value, this.textValue, new TagPathMatcher(this.tagsStack,node));
+
+      if(!resultTag) return;
+    }
+
+    //set parent node in scope
+    let arr = this.tagsStack.pop(); 
+    let parentTag = arr[2];
+    parentTag=this._addChildTo(resultTag.tagName, resultTag.value, parentTag);
+
+    this.tagName = arr[0];
+    this.textValue = arr[1];
+    this.value = parentTag;
+  }
+
+  _addChild(key, val){
+    if(typeof this.value === "string"){
+      this.value = { [this.options.nameFor.text] : this.value };
+    }
+
+    this._addChildTo(key, val, this.value);
+    // this.currentNode.leafType = false;
+    this.attributes = {};
+  }
+
+  _addChildTo(key, val, node){
+    if(typeof node === 'string') node = {};
+    if(!node[key]){
+      node[key] = val;
+    }else{ //Repeated
+      if(!Array.isArray(node[key])){ //but not stored as array
+        node[key] = [node[key]];
+      }
+      node[key].push(val);
+    }
+    return node;
+  }
+
+
+  /**
+   * Add text value child node 
+   * @param {string} text 
+   */
+  addValue(text){
+    //TODO: use bytes join
+    if(this.textValue.length > 0) this.textValue += " " + text;
+    else this.textValue = text;
+  }
+
+  addPi(name){
+    let value = "";
+    if( !isEmpty(this.attributes)){
+      value = {};
+      if(this.options.attributes.groupBy){
+        value[this.options.attributes.groupBy] = this.attributes;
+      }else{
+        value = this.attributes;
+      }
+    }
+    this._addChild(name, value);
+    
+  }
+  getOutput(){
+    return this.value;
+  }
+}
+
+function isEmpty(obj) {
+  return Object.keys(obj).length === 0;
+}