fast-xml-parser 4.3.4 → 4.3.6

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 Note: If you find missing information about particular minor version, that version must have been changed without any functional change in this library.
 
+**4.3.6 / 2024-03-16**
+* Add support for parsing HTML numeric entities (#645) (By [Jonas Schade ](https://github.com/DerZade))
+
+**4.3.5 / 2024-02-24**
+* code for v5 is added for experimental use
+
 **4.3.4 / 2024-01-10**
 * fix: Don't escape entities in CDATA sections (#633) (By [wackbyte](https://github.com/wackbyte))
 

package/README.md

@@ -11,7 +11,8 @@
 
 Validate XML, Parse XML to JS Object, or Build XML from JS Object without C/C++ based libraries and no callback.
 
-<font size="6">I need a Career advice. I've posted the query on my <a href="github.com/amitguptagwl">profile</a>. Your support would be appreciable.</font>
+> XML Parser v5 is added for experimental use
+> https://solothought.com
 
 Sponsor this project 👉 
 <a href="https://github.com/sponsors/NaturalIntelligence"> 
@@ -91,6 +92,11 @@ If you want to be an anonymous user of this application and don't want to be hig
 * Supports parsing of PI (Processing Instruction) tags with XML declaration tags
 * And many more other features.
 
+## v5
+I developed v5 in Apr 2023. And I didn't get the chance to complete all the features. I've ensured that new features don't impact performance. With v5, you have more control on parsing output. Check [docs](./docs/v5) for syntax help and basic understanding.
+
+Please leave a comment in discussion forum for your suggestions and if you really need v5.
+
 ## How to use
 
 To use as package dependency
@@ -174,19 +180,6 @@ Check lib folder for different browser bundles
 
 [![](static/img/ni_ads_ads.gif)](https://github.com/NaturalIntelligence/ads/)
 
-## Our other projects and research you must try
-
-* **[BigBit standard](https://github.com/amitguptagwl/bigbit)** : 
-  * Single text encoding to replace UTF-8, UTF-16, UTF-32 and more with less memory.
-  * Single Numeric datatype alternative of integer, float, double, long, decimal and more without precision loss.
-* **[Cytorus](https://github.com/NaturalIntelligence/cytorus)**:  Be specific and flexible while running E2E tests.
-  * Run tests only for a particular User Story
-  * Run tests for a route or from a route
-  * Customizable reporting
-  * Central dashboard for better monitoring
-  * Options to integrate E2E tests with Jira, Github etc using Central dashboard `Tian`.
-* **[Stubmatic](https://github.com/NaturalIntelligence/Stubmatic)** : Create fake webservices, DynamoDB or S3 servers, Manage fake/mock stub data, Or fake any HTTP(s) call.
-
 
 ## Supporters
 ### Contributors

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fast-xml-parser",
-  "version": "4.3.4",
+  "version": "4.3.6",
   "description": "Validate XML, Parse XML, Build XML without C/C++ based libraries",
   "main": "./src/fxp.js",
   "scripts": {

package/src/v5/CharsSymbol.js

@@ -0,0 +1,16 @@
+modules.export = {
+  "<" : "<", //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/v5/EntitiesParser.js

@@ -0,0 +1,107 @@
+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)) },
+};
+
+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;
+}
+
+module.exports = EntitiesParser;

package/src/v5/OptionsBuilder.js

@@ -0,0 +1,64 @@
+
+const JsObjOutputBuilder = require("./OutputBuilders/JsObjBuilder");
+
+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(),
+};
+   
+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];
+      }
+    }
+  }
+}
+
+exports.buildOptions = buildOptions;
+exports.defaultOptions = defaultOptions;

package/src/v5/OutputBuilders/BaseOutputBuilder.js

@@ -0,0 +1,71 @@
+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 = {}
+  }
+}
+
+module.exports = BaseOutputBuilder;

package/src/v5/OutputBuilders/JsArrBuilder.js

@@ -0,0 +1,103 @@
+const {buildOptions,registerCommonValueParsers} = require("./ParserOptionsBuilder");
+
+class OutputBuilder{
+  constructor(options){
+    this.options = buildOptions(options);
+      this.registeredParsers = registerCommonValueParsers();
+    }
+    
+    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';
+const BaseOutputBuilder = require("./BaseOutputBuilder");
+
+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/v5/OutputBuilders/JsMinArrBuilder.js

@@ -0,0 +1,102 @@
+const {buildOptions,registerCommonValueParsers} = require("./ParserOptionsBuilder");
+
+class OutputBuilder{
+  constructor(options){
+    this.options = buildOptions(options);
+      this.registeredParsers = registerCommonValueParsers();
+    }
+    
+    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);
+  }
+}
+
+const BaseOutputBuilder = require("./BaseOutputBuilder");
+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];
+  }
+}
+
+module.exports = OutputBuilder;

package/src/v5/OutputBuilders/JsObjBuilder.js

@@ -0,0 +1,156 @@
+
+
+const {buildOptions,registerCommonValueParsers} = require("./ParserOptionsBuilder");
+
+class OutputBuilder{
+  constructor(builderOptions){
+      this.options = buildOptions(builderOptions);
+      this.registeredParsers = registerCommonValueParsers();
+  }
+
+  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);
+  }
+}
+
+const BaseOutputBuilder = require("./BaseOutputBuilder");
+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;
+}
+
+module.exports = OutputBuilder;