fast-xml-parser 4.3.5 → 4.4.0

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 Note: If you find missing information about particular minor version, that version must have been changed without any functional change in this library.
 
+**4.4.0 / 2024-05-18**
+* fix #654: parse attribute list correctly for self closing stop node.
+* fix: validator bug when closing tag is not opened. (#647) (By [Ryosuke Fukatani](https://github.com/RyosukeFukatani))
+* fix #581: typings; return type of `tagValueProcessor` & `attributeValueProcessor` (#582) (By [monholm]())
+
+**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
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fast-xml-parser",
-  "version": "4.3.5",
+  "version": "4.4.0",
   "description": "Validate XML, Parse XML, Build XML without C/C++ based libraries",
   "main": "./src/fxp.js",
   "scripts": {

package/src/fxp.d.ts

@@ -345,7 +345,7 @@ type XmlBuilderOptions = {
    * 
    * Defaults to `(tagName, val, jPath, hasAttributes, isLeafNode) => val`
    */
-  tagValueProcessor?: (name: string, value: unknown) => string;
+  tagValueProcessor?: (name: string, value: unknown) => unknown;
 
   /**
    * Control how attribute value should be parsed
@@ -358,7 +358,7 @@ type XmlBuilderOptions = {
    * 
    * Defaults to `(attrName, val, jPath) => val`
    */
-  attributeValueProcessor?: (name: string, value: unknown) => string;
+  attributeValueProcessor?: (name: string, value: unknown) => unknown;
 
   /**
    * Whether to process default and DOCTYPE entities

package/src/v5/EntitiesParser.js

@@ -13,6 +13,8 @@ const htmlEntities = {
     "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{

package/src/v5/OptionsBuilder.js

@@ -1,5 +1,5 @@
 
-const JsArrBuilder = require("./OutputBuilders/JsArrBuilder");
+const JsObjOutputBuilder = require("./OutputBuilders/JsObjBuilder");
 
 const defaultOptions = {
   preserveOrder: false,
@@ -17,12 +17,11 @@ const defaultOptions = {
       text: '#text'
     },
     separateTextProperty: false,
-    valueParsers: []
   },
   attributes:{
     ignore: false,
     booleanType: true,
-    entities: true
+    entities: true,
   },
 
   // select: ["img[src]"],
@@ -33,21 +32,13 @@ const defaultOptions = {
 
   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 JsArrBuilder(),
+  OutputBuilder: new JsObjOutputBuilder(),
 };
    
 const buildOptions = function(options) {
   const finalOptions = { ... defaultOptions};
-  finalOptions.tags.valueParsers.push("trim");
-  finalOptions.tags.valueParsers.push("entities");
-  if(!this.preserveOrder)
-    finalOptions.tags.valueParsers.push("join");
-  finalOptions.tags.valueParsers.push("boolean");
-  finalOptions.tags.valueParsers.push("number");
-  finalOptions.tags.valueParsers.push("currency");
-  finalOptions.tags.valueParsers.push("date");
   copyProperties(finalOptions,options)
-  return  finalOptions;
+  return finalOptions;
 };
 
 function copyProperties(target, source) {

package/src/v5/OutputBuilders/BaseOutputBuilder.js

@@ -7,7 +7,7 @@ class BaseOutputBuilder{
     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;
+      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);
@@ -21,10 +21,12 @@ class BaseOutputBuilder{
    */
     parseValue = function(val, valParsers){
       for (let i = 0; i < valParsers.length; i++) {
-        let valParser = this.registeredParsers[valParsers[i]];
+        let valParser = valParsers[i];
+        if(typeof valParser === "string"){
+          valParser = this.registeredParsers[valParser];
+        }
         if(valParser){
           val = valParser.parse(val);
-          // if(!valParser.chainable) break;
         }
       }
       return val;

package/src/v5/OutputBuilders/JsArrBuilder.js

@@ -10,8 +10,8 @@ class OutputBuilder{
       this.registeredParsers[name] = parserInstance;
     }
 
-  getInstance(){
-    return new JsArrBuilder(this.options, this.registeredParsers);
+  getInstance(parserOptions){
+    return new JsArrBuilder(parserOptions, this.options, this.registeredParsers);
   }
 }
 
@@ -20,9 +20,10 @@ const BaseOutputBuilder = require("./BaseOutputBuilder");
 
 class JsArrBuilder extends BaseOutputBuilder{
 
-  constructor(options,registeredParsers) {
+  constructor(parserOptions, options,registeredParsers) {
     super();
     this.tagsStack = [];
+    this.parserOptions = parserOptions;
     this.options = options;
     this.registeredParsers = registeredParsers;
 

package/src/v5/OutputBuilders/JsMinArrBuilder.js

@@ -10,8 +10,8 @@ class OutputBuilder{
       this.registeredParsers[name] = parserInstance;
     }
 
-  getInstance(){
-    return new JsMinArrBuilder(this.options, this.registeredParsers);
+  getInstance(parserOptions){
+    return new JsMinArrBuilder(parserOptions, this.options, this.registeredParsers);
   }
 }
 
@@ -20,9 +20,10 @@ const rootName = '^';
 
 class JsMinArrBuilder extends BaseOutputBuilder{
 
-  constructor(options,registeredParsers) {
+  constructor(parserOptions, options,registeredParsers) {
     super();
     this.tagsStack = [];
+    this.parserOptions = parserOptions;
     this.options = options;
     this.registeredParsers = registeredParsers;
 

package/src/v5/OutputBuilders/JsObjBuilder.js

@@ -3,8 +3,8 @@
 const {buildOptions,registerCommonValueParsers} = require("./ParserOptionsBuilder");
 
 class OutputBuilder{
-  constructor(options){
-      this.options = buildOptions(options);
+  constructor(builderOptions){
+      this.options = buildOptions(builderOptions);
       this.registeredParsers = registerCommonValueParsers();
   }
 
@@ -12,8 +12,8 @@ class OutputBuilder{
     this.registeredParsers[name] = parserInstance;
   }
 
-  getInstance(){
-    return new JsObjBuilder(this.options, this.registeredParsers);
+  getInstance(parserOptions){
+    return new JsObjBuilder(parserOptions, this.options, this.registeredParsers);
   }
 }
 
@@ -22,11 +22,12 @@ const rootName = '^';
 
 class JsObjBuilder extends BaseOutputBuilder{
 
-  constructor(options,registeredParsers) {
+  constructor(parserOptions, builderOptions,registeredParsers) {
     super();
     //hold the raw detail of a tag and sequence with reference to the output
     this.tagsStack = [];
-    this.options = options;
+    this.parserOptions = parserOptions;
+    this.options = builderOptions;
     this.registeredParsers = registeredParsers;
 
     this.root = {};
@@ -75,13 +76,13 @@ class JsObjBuilder extends BaseOutputBuilder{
 
     
     let resultTag= {
-      tagName: this.tagName,
+      tagName: tagName,
       value: value
     };
 
     if(this.options.onTagClose !== undefined){
       //TODO TagPathMatcher 
-      resultTag = this.options.onClose(this.tagName, value, this.textValue, new TagPathMatcher(this.tagsStack,node));
+      resultTag = this.options.onClose(tagName, value, this.textValue, new TagPathMatcher(this.tagsStack,node));
 
       if(!resultTag) return;
     }

package/src/v5/OutputBuilders/ParserOptionsBuilder.js

@@ -36,22 +36,24 @@ const defaultOptions={
     ]
   }
 }
+
+//TODO
+const withJoin = ["trim","join", /*"entities",*/"number","boolean","currency"/*, "date"*/]
+const withoutJoin = ["trim", /*"entities",*/"number","boolean","currency"/*, "date"*/]
+
 function buildOptions(options){
   //clone
   const finalOptions = { ... defaultOptions};
 
   //add config missed in cloning
-  finalOptions.tags.valueParsers.push("trim")
-  finalOptions.tags.valueParsers.push("boolean")
-  finalOptions.tags.valueParsers.push("number")
-  finalOptions.tags.valueParsers.push("currency")
+  finalOptions.tags.valueParsers.push(...withJoin)
+  if(!this.preserveOrder)
+    finalOptions.tags.valueParsers.push(...withoutJoin);
 
   //add config missed in cloning
-  finalOptions.attributes.valueParsers.push("trim")
-  finalOptions.attributes.valueParsers.push("boolean")
-  finalOptions.attributes.valueParsers.push("number")
-  finalOptions.attributes.valueParsers.push("currency")
+  finalOptions.attributes.valueParsers.push(...withJoin)
 
+  //override configuration
   copyProperties(finalOptions,options);
   return finalOptions;
 }

package/src/v5/valueParsers/EntitiesParser.js

@@ -13,6 +13,8 @@ const htmlEntities = {
     "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{

package/src/validator.js

@@ -103,6 +103,8 @@ exports.validate = function (xmlData, options) {
             return getErrorObject('InvalidTag', "Closing tag '"+tagName+"' doesn't have proper closing.", getLineNumberForPosition(xmlData, i));
           } else if (attrStr.trim().length > 0) {
             return getErrorObject('InvalidTag', "Closing tag '"+tagName+"' can't have attributes or invalid starting.", getLineNumberForPosition(xmlData, tagStartPos));
+          } else if (tags.length === 0) {
+            return getErrorObject('InvalidTag', "Closing tag '"+tagName+"' has not been opened.", getLineNumberForPosition(xmlData, tagStartPos));
           } else {
             const otg = tags.pop();
             if (tagName !== otg.tagName) {

package/src/xmlparser/OrderedObjParser.js

@@ -40,6 +40,8 @@ class OrderedObjParser{
       "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)) },
     };
     this.addExternalEntities = addExternalEntities;
     this.parseXml = parseXml;
@@ -309,10 +311,18 @@ const parseXml = function(xmlData) {
           let tagContent = "";
           //self-closing tag
           if(tagExp.length > 0 && tagExp.lastIndexOf("/") === tagExp.length - 1){
+            if(tagName[tagName.length - 1] === "/"){ //remove trailing '/'
+              tagName = tagName.substr(0, tagName.length - 1);
+              jPath = jPath.substr(0, jPath.length - 1);
+              tagExp = tagName;
+            }else{
+              tagExp = tagExp.substr(0, tagExp.length - 1);
+            }
             i = result.closeIndex;
           }
           //unpaired tag
           else if(this.options.unpairedTags.indexOf(tagName) !== -1){
+            
             i = result.closeIndex;
           }
           //normal tag