fast-xml-parser - npm Package Compare versions

Comparing version 2.8.3 to 2.9.0

bin/parser.js

@@ -154,5 +154,3 @@ var getAllMatches = require("./util").getAllMatches;
 
-//var attrsRegx = new RegExp("(\\S+)=\\s*[\"']?((?:.(?![\"']?\\s+(?:\\S+)=|[>\"']))+.)[\"']?","g");
-//var attrsRegx = new RegExp("(\\S+)=\\s*(['\"])((?:.(?!\\2))*.)","g");
-var attrsRegx = new RegExp("(\\S+)\\s*=\\s*(['\"])(.*?)\\2","g");
+var attrsRegx = new RegExp("([\\w\\-\\.\\:]+)\\s*=\\s*(['\"])(.*?)\\2","g");
 function buildAttributesArr(attrStr,ignore,prefix,attrNodeName,ignoreNS,conversion){
@@ -171,2 +169,3 @@ attrStr = attrStr || attrStr.trim();
             var attrName = prefix + resolveNameSpace( matches[i][1],ignoreNS);
+            
             attrsCollection[attrName] = parseValue(matches[i][3],conversion);
@@ -173,0 +172,0 @@ }

bin/validator.js

@@ -7,82 +7,209 @@ var util = require("./util");
     xmlData = xmlData.replace(/\n/g,"");//make it single line
-    xmlData = xmlData.replace(/(<!\[CDATA\[.*?\]\]>)/g,"");//Remove all CDATA
-    xmlData = xmlData.replace(/(<!--.*?(?:-->))/g,"");//Remove all comments
-    if(validateAttributes(xmlData) !== true) return false;
-    xmlData = xmlData.replace(/(\s+(?:[\w:\-]+)\s*=\s*(['\"]).*?\2)/g,"");//Remove all attributes
-    xmlData = xmlData.replace(/(^\s*<\?xml\s*\?>)/g,"");//Remove XML starting tag
-    if(xmlData.indexOf("<![CDATA[") > 0 || xmlData.indexOf("<!--") > 0 ) return false;
-    var tags = util.getAllMatches(xmlData,tagsPattern);
-    if(tags.length === 0) return false; //non xml string
-    
-    var result = checkForMatchingTag(tags,0);
-    
+    xmlData = xmlData.replace(/(^\s*<\?xml.*?\?>)/g,"");//Remove XML starting tag
+    xmlData = xmlData.replace(/(<!DOCTYPE[\s\w\"\.\/\-\:]+(\[.*\])*\s*>)/g,"");//Remove DOCTYPE
 
-    if(result !== true) return false; else return true; 
-    
-}
+    var tags = [];
+    for (var i = 0; i < xmlData.length; i++) {
 
+        if(xmlData[i] === "<"){//starting of tag
+            //read until you reach to '>' avoiding any '>' in attribute value
+            
+            i++;
+            
+            if(xmlData[i] === "!"){
+                i = readCommentAndCDATA(xmlData,i);
+                continue;
+            }else{
+                var closingTag = false;
+                if(xmlData[i] === "/"){//closing tag
+                    closingTag = true;
+                    i++;
+                }
+                //read tagname
+                var tagName = "";
+                for(;i < xmlData.length 
+                    && xmlData[i] !== ">" 
+                    && xmlData[i] !== " "
+                    && xmlData[i] !== "\t" ; i++) {
 
-var startsWithXML = new RegExp("^[Xx][Mm][Ll]");
-var startsWith = new RegExp("^([a-zA-Z]|_)[\\w\.\\-_:]*");
+                    tagName +=xmlData[i];
+                }
+                tagName = tagName.trim();
+                
+                if(tagName[tagName.length-1] === "/"){//self closing tag without attributes
+                    tagName = tagName.substring(0,tagName.length-2);
+                    return validateTagName(tagName);
+                }
+                if(!validateTagName(tagName)) return false;
 
-function validateTagName(tagname){
-    if(util.doesMatch(tagname,startsWithXML)) return false;
-    else if(util.doesNotMatch(tagname,startsWith)) return false;
-    else return true;
-}
-
-var attrStringPattern = new RegExp("<[\\w:\\-_\.]+(.*?)\/?>","g");
-var attrPattern = new RegExp("\\s+([\\w:\-]+)\\s*=\\s*(['\"])(.*?)\\2","g");
-function validateAttributes(xmlData){
-    var attrStrings = util.getAllMatches(xmlData,attrStringPattern);
-    for (i=0;i<attrStrings.length;i++){
-        if(attrStrings[i][1].trim().length > 0 && attrStrings[i][1].trim().length < 4){ //invalid attributes 
-            return false;
-        }else if(attrStrings[i][1].trim().length !== 0){
-            var attrsList = util.getAllMatches(attrStrings[i][1],attrPattern);
-            var attrNames=[];
-            for (j=0;j<attrsList.length;j++){
-                if(attrNames.hasOwnProperty(attrsList[j][1])){//duplicate attributes
-                    return false;
+                
+                var attrStr = "";
+                var startChar = "";
+                for(;i < xmlData.length ;i++){
+                    if(xmlData[i] === '"' || xmlData[i] === "'"){
+                        if(startChar === ""){
+                            startChar = xmlData[i];
+                        }else{
+                            startChar = "";
+                        }
+                    }else if(xmlData[i] === ">"){
+                        if(startChar === ""){
+                            break;
+                        }
+                    }
+                    attrStr += xmlData[i];
+                }
+                if(startChar !== "") return false;//You have forgot to close the quote
+                attrStr = attrStr.trim();
+                
+                if(attrStr[attrStr.length-1] === "/" ){//self closing tag
+                    attrStr = attrStr.substring(0,attrStr.length-2);
+                    
+                    if(!validateAttributeString(attrStr)){
+                        return false;
+                    }else{
+                        
+                        continue;
+                    }
+                }else if(closingTag){
+                    if(attrStr.length > 0){
+                        return false;
+                        //throw new Error("XML validation error: closing tag should not have any attribute");
+                    }else{
+                        var otg = tags.pop();    
+                        if(tagName !== otg){
+                            return false;
+                            //throw new Error("XML validation error: no mathicng closing tag");
+                        }
+                    }
                 }else{
-                    attrNames[attrsList[j][1]]=1;
-                    //validate attribute value
-                    //if(!validateAttrValue(attrsList[3])) return false;
+                    if(!validateAttributeString(attrStr)){
+                        return false;
+                    }
+                    tags.push(tagName);
                 }
+
+                //skip tag text value
+                //It may include comments and CDATA value
+                for(i++;i < xmlData.length ; i++){
+                    if(xmlData[i] === "<"){
+                        if(xmlData[i+1] === "!"){//comment or CADATA
+                            i++;
+                            i = readCommentAndCDATA(xmlData,i);
+                            continue;
+                        }else{
+                            break;
+                        }
+                    }
+                }//end of reading tag text value
+                if(xmlData[i] === "<") i--;
             }
+        }else{
+            
+            if(xmlData[i] === " " || xmlData[i] === "\t") continue;
+            return false;
         }
     }
+
+    
+    if(tags.length > 0){
+        return false;
+        //throw new Error("XML validation error");
+    }
+    
     return true;
 }
 
-function checkForMatchingTag(tags,i){
-    if(tags.length === i) {
-        return true;
-    }else if(tags[i][0].indexOf("</") === 0) {//closing tag
-        return i;
-    }else if(tags[i][0].indexOf("/>") === tags[i][0].length-2){//Self closing tag
-        if(validateTagName(tags[i][0].substring(1)) === false) return -1;
-        return checkForMatchingTag(tags,i+1);
+function readCommentAndCDATA(xmlData,i){
+    if(xmlData.length > i+5 && xmlData[i+1] === "-" && xmlData[i+2] === "-"){//comment
+        for(i+=3;i<xmlData.length;i++){
+            if(xmlData[i] === "-" && xmlData[i+1] === "-" && xmlData[i+2] === ">"){
+                i+=2;
+                break;
+            }
+        }
+    }else if( xmlData.length > i+9 
+        && xmlData[i+1] === "[" 
+        && xmlData[i+2] === "C"
+        && xmlData[i+3] === "D"
+        && xmlData[i+4] === "A"
+        && xmlData[i+5] === "T"
+        && xmlData[i+6] === "A"
+        && xmlData[i+7] === "["){
 
-    }else if(tags.length > i+1){
-        if(tags[i+1][0].indexOf("</") === 0){//next tag
-            if(validateTagName(tags[i][1]) === false) return -1;
-            if(tags[i][1] === tags[i+1][1]) {//matching with next closing tag
-                return checkForMatchingTag(tags,i+2);
-            }else {
-                return -1;//not matching
+        for(i+=8;i<xmlData.length;i++){
+            if(xmlData[i] === "]" && xmlData[i+1] === "]" && xmlData[i+2] === ">" ){
+                i+=2;
+                break;
             }
-        }else
-            var nextIndex = checkForMatchingTag(tags,i+1);
-            if(nextIndex !== -1 && tags[nextIndex] !== undefined && tags[nextIndex][0].indexOf("</") === 0){
-                if(validateTagName(tags[i][1]) === false) return -1;
-                if(tags[i][1] === tags[nextIndex][1]) {
-                    return checkForMatchingTag(tags,nextIndex+1);
-                }else {
-                    return -1;//not matching
-                }
-            }
+        }
     }
-    return -1;
+
+    return i;
 }
+//attr, ="sd", a="amit's", a="sd"b="saf", 
+function validateAttributeString(attrStr){
+    var attrNames = [];
+    for(var i=0; i< attrStr.length; i++){
+        var startChar = "";
+        //read attribute name
+        var attrName = "";
+        for(;i < attrStr.length && attrStr[i] !== "=" ; i++) {
+            attrName +=attrStr[i];
+        }
+        //validate attrName
+        attrName = attrName.trim();
 
+        
+        
+        if(!attrNames.hasOwnProperty(attrName)){
+            attrNames[attrName]=1;
+        }else{
+            return false;
+        }
+        if(!validateAttrName(attrName)){
+            return false;
+        }
+        i++;
+        
+        //skip whitespaces
+        for(;i < attrStr.length 
+            && (attrStr[i] === " "
+            || attrStr[i] === "\t") ; i++);
+
+        //read attribute value
+        startChar = attrStr[i++];
+        /*if(startChar !== "'" || startChar !== '"'){
+            
+            return false;
+        }*/
+        var attrVal = "";
+        for(;i < attrStr.length && attrStr[i] !== startChar; i++) {
+            attrVal +=attrStr[i];
+        }
+        
+        //validate attrVal
+
+        if(startChar !== ""){
+            startChar = "";
+        }
+    }
+
+    return true;
+}
+
+var validAttrRegxp = new RegExp("^[_a-zA-Z][\\w\\-\\.\\:]*$");
+
+function validateAttrName(attrName){
+    return util.doesMatch(attrName,validAttrRegxp);
+}
+var startsWithXML = new RegExp("^[Xx][Mm][Ll]");
+var startsWith = new RegExp("^([a-zA-Z]|_)[\\w\.\\-_:]*");
+
+function validateTagName(tagname){
+    if(util.doesMatch(tagname,startsWithXML)) return false;
+    else if(util.doesNotMatch(tagname,startsWith)) return false;
+    else return true;
+}
+
+

lib/parser.js

@@ -155,5 +155,3 @@ (function(f){if(typeof exports==="object"&&typeof module!=="undefined"){module.exports=f()}else if(typeof define==="function"&&define.amd){define([],f)}else{var g;if(typeof window!=="undefined"){g=window}else if(typeof global!=="undefined"){g=global}else if(typeof self!=="undefined"){g=self}else{g=this}g.parser = f()}})(function(){var define,module,exports;return (function e(t,n,r){function s(o,u){if(!n[o]){if(!t[o]){var a=typeof require=="function"&&require;if(!u&&a)return a(o,!0);if(i)return i(o,!0);var f=new Error("Cannot find module '"+o+"'");throw f.code="MODULE_NOT_FOUND",f}var l=n[o]={exports:{}};t[o][0].call(l.exports,function(e){var n=t[o][1][e];return s(n?n:e)},l,l.exports,e,t,n,r)}return n[o].exports}var i=typeof require=="function"&&require;for(var o=0;o<r.length;o++)s(r[o]);return s})({1:[function(require,module,exports){
 
-//var attrsRegx = new RegExp("(\\S+)=\\s*[\"']?((?:.(?![\"']?\\s+(?:\\S+)=|[>\"']))+.)[\"']?","g");
-//var attrsRegx = new RegExp("(\\S+)=\\s*(['\"])((?:.(?!\\2))*.)","g");
-var attrsRegx = new RegExp("(\\S+)\\s*=\\s*(['\"])(.*?)\\2","g");
+var attrsRegx = new RegExp("([\\w\\-\\.\\:]+)\\s*=\\s*(['\"])(.*?)\\2","g");
 function buildAttributesArr(attrStr,ignore,prefix,attrNodeName,ignoreNS,conversion){
@@ -172,2 +170,3 @@ attrStr = attrStr || attrStr.trim();
             var attrName = prefix + resolveNameSpace( matches[i][1],ignoreNS);
+            
             attrsCollection[attrName] = parseValue(matches[i][3],conversion);
@@ -243,85 +242,212 @@ }
     xmlData = xmlData.replace(/\n/g,"");//make it single line
-    xmlData = xmlData.replace(/(<!\[CDATA\[.*?\]\]>)/g,"");//Remove all CDATA
-    xmlData = xmlData.replace(/(<!--.*?(?:-->))/g,"");//Remove all comments
-    if(validateAttributes(xmlData) !== true) return false;
-    xmlData = xmlData.replace(/(\s+(?:[\w:\-]+)\s*=\s*(['\"]).*?\2)/g,"");//Remove all attributes
-    xmlData = xmlData.replace(/(^\s*<\?xml\s*\?>)/g,"");//Remove XML starting tag
-    if(xmlData.indexOf("<![CDATA[") > 0 || xmlData.indexOf("<!--") > 0 ) return false;
-    var tags = util.getAllMatches(xmlData,tagsPattern);
-    if(tags.length === 0) return false; //non xml string
-    
-    var result = checkForMatchingTag(tags,0);
-    
+    xmlData = xmlData.replace(/(^\s*<\?xml.*?\?>)/g,"");//Remove XML starting tag
+    xmlData = xmlData.replace(/(<!DOCTYPE[\s\w\"\.\/\-\:]+(\[.*\])*\s*>)/g,"");//Remove DOCTYPE
 
-    if(result !== true) return false; else return true; 
-    
-}
+    var tags = [];
+    for (var i = 0; i < xmlData.length; i++) {
 
+        if(xmlData[i] === "<"){//starting of tag
+            //read until you reach to '>' avoiding any '>' in attribute value
+            
+            i++;
+            
+            if(xmlData[i] === "!"){
+                i = readCommentAndCDATA(xmlData,i);
+                continue;
+            }else{
+                var closingTag = false;
+                if(xmlData[i] === "/"){//closing tag
+                    closingTag = true;
+                    i++;
+                }
+                //read tagname
+                var tagName = "";
+                for(;i < xmlData.length 
+                    && xmlData[i] !== ">" 
+                    && xmlData[i] !== " "
+                    && xmlData[i] !== "\t" ; i++) {
 
-var startsWithXML = new RegExp("^[Xx][Mm][Ll]");
-var startsWith = new RegExp("^([a-zA-Z]|_)[\\w\.\\-_:]*");
+                    tagName +=xmlData[i];
+                }
+                tagName = tagName.trim();
+                
+                if(tagName[tagName.length-1] === "/"){//self closing tag without attributes
+                    tagName = tagName.substring(0,tagName.length-2);
+                    return validateTagName(tagName);
+                }
+                if(!validateTagName(tagName)) return false;
 
-function validateTagName(tagname){
-    if(util.doesMatch(tagname,startsWithXML)) return false;
-    else if(util.doesNotMatch(tagname,startsWith)) return false;
-    else return true;
-}
-
-var attrStringPattern = new RegExp("<[\\w:\\-_\.]+(.*?)\/?>","g");
-var attrPattern = new RegExp("\\s+([\\w:\-]+)\\s*=\\s*(['\"])(.*?)\\2","g");
-function validateAttributes(xmlData){
-    var attrStrings = util.getAllMatches(xmlData,attrStringPattern);
-    for (i=0;i<attrStrings.length;i++){
-        if(attrStrings[i][1].trim().length > 0 && attrStrings[i][1].trim().length < 4){ //invalid attributes 
-            return false;
-        }else if(attrStrings[i][1].trim().length !== 0){
-            var attrsList = util.getAllMatches(attrStrings[i][1],attrPattern);
-            var attrNames=[];
-            for (j=0;j<attrsList.length;j++){
-                if(attrNames.hasOwnProperty(attrsList[j][1])){//duplicate attributes
-                    return false;
+                
+                var attrStr = "";
+                var startChar = "";
+                for(;i < xmlData.length ;i++){
+                    if(xmlData[i] === '"' || xmlData[i] === "'"){
+                        if(startChar === ""){
+                            startChar = xmlData[i];
+                        }else{
+                            startChar = "";
+                        }
+                    }else if(xmlData[i] === ">"){
+                        if(startChar === ""){
+                            break;
+                        }
+                    }
+                    attrStr += xmlData[i];
+                }
+                if(startChar !== "") return false;//You have forgot to close the quote
+                attrStr = attrStr.trim();
+                
+                if(attrStr[attrStr.length-1] === "/" ){//self closing tag
+                    attrStr = attrStr.substring(0,attrStr.length-2);
+                    
+                    if(!validateAttributeString(attrStr)){
+                        return false;
+                    }else{
+                        
+                        continue;
+                    }
+                }else if(closingTag){
+                    if(attrStr.length > 0){
+                        return false;
+                        //throw new Error("XML validation error: closing tag should not have any attribute");
+                    }else{
+                        var otg = tags.pop();    
+                        if(tagName !== otg){
+                            return false;
+                            //throw new Error("XML validation error: no mathicng closing tag");
+                        }
+                    }
                 }else{
-                    attrNames[attrsList[j][1]]=1;
-                    //validate attribute value
-                    //if(!validateAttrValue(attrsList[3])) return false;
+                    if(!validateAttributeString(attrStr)){
+                        return false;
+                    }
+                    tags.push(tagName);
                 }
+
+                //skip tag text value
+                //It may include comments and CDATA value
+                for(i++;i < xmlData.length ; i++){
+                    if(xmlData[i] === "<"){
+                        if(xmlData[i+1] === "!"){//comment or CADATA
+                            i++;
+                            i = readCommentAndCDATA(xmlData,i);
+                            continue;
+                        }else{
+                            break;
+                        }
+                    }
+                }//end of reading tag text value
+                if(xmlData[i] === "<") i--;
             }
+        }else{
+            
+            if(xmlData[i] === " " || xmlData[i] === "\t") continue;
+            return false;
         }
     }
+
+    
+    if(tags.length > 0){
+        return false;
+        //throw new Error("XML validation error");
+    }
+    
     return true;
 }
 
-function checkForMatchingTag(tags,i){
-    if(tags.length === i) {
-        return true;
-    }else if(tags[i][0].indexOf("</") === 0) {//closing tag
-        return i;
-    }else if(tags[i][0].indexOf("/>") === tags[i][0].length-2){//Self closing tag
-        if(validateTagName(tags[i][0].substring(1)) === false) return -1;
-        return checkForMatchingTag(tags,i+1);
+function readCommentAndCDATA(xmlData,i){
+    if(xmlData.length > i+5 && xmlData[i+1] === "-" && xmlData[i+2] === "-"){//comment
+        for(i+=3;i<xmlData.length;i++){
+            if(xmlData[i] === "-" && xmlData[i+1] === "-" && xmlData[i+2] === ">"){
+                i+=2;
+                break;
+            }
+        }
+    }else if( xmlData.length > i+9 
+        && xmlData[i+1] === "[" 
+        && xmlData[i+2] === "C"
+        && xmlData[i+3] === "D"
+        && xmlData[i+4] === "A"
+        && xmlData[i+5] === "T"
+        && xmlData[i+6] === "A"
+        && xmlData[i+7] === "["){
 
-    }else if(tags.length > i+1){
-        if(tags[i+1][0].indexOf("</") === 0){//next tag
-            if(validateTagName(tags[i][1]) === false) return -1;
-            if(tags[i][1] === tags[i+1][1]) {//matching with next closing tag
-                return checkForMatchingTag(tags,i+2);
-            }else {
-                return -1;//not matching
+        for(i+=8;i<xmlData.length;i++){
+            if(xmlData[i] === "]" && xmlData[i+1] === "]" && xmlData[i+2] === ">" ){
+                i+=2;
+                break;
             }
-        }else
-            var nextIndex = checkForMatchingTag(tags,i+1);
-            if(nextIndex !== -1 && tags[nextIndex] !== undefined && tags[nextIndex][0].indexOf("</") === 0){
-                if(validateTagName(tags[i][1]) === false) return -1;
-                if(tags[i][1] === tags[nextIndex][1]) {
-                    return checkForMatchingTag(tags,nextIndex+1);
-                }else {
-                    return -1;//not matching
-                }
-            }
+        }
     }
-    return -1;
+
+    return i;
 }
+//attr, ="sd", a="amit's", a="sd"b="saf", 
+function validateAttributeString(attrStr){
+    var attrNames = [];
+    for(var i=0; i< attrStr.length; i++){
+        var startChar = "";
+        //read attribute name
+        var attrName = "";
+        for(;i < attrStr.length && attrStr[i] !== "=" ; i++) {
+            attrName +=attrStr[i];
+        }
+        //validate attrName
+        attrName = attrName.trim();
 
+        
+        
+        if(!attrNames.hasOwnProperty(attrName)){
+            attrNames[attrName]=1;
+        }else{
+            return false;
+        }
+        if(!validateAttrName(attrName)){
+            return false;
+        }
+        i++;
+        
+        //skip whitespaces
+        for(;i < attrStr.length 
+            && (attrStr[i] === " "
+            || attrStr[i] === "\t") ; i++);
 
+        //read attribute value
+        startChar = attrStr[i++];
+        /*if(startChar !== "'" || startChar !== '"'){
+            
+            return false;
+        }*/
+        var attrVal = "";
+        for(;i < attrStr.length && attrStr[i] !== startChar; i++) {
+            attrVal +=attrStr[i];
+        }
+        
+        //validate attrVal
+
+        if(startChar !== ""){
+            startChar = "";
+        }
+    }
+
+    return true;
+}
+
+var validAttrRegxp = new RegExp("^[_a-zA-Z][\\w\\-\\.\\:]*$");
+
+function validateAttrName(attrName){
+    return util.doesMatch(attrName,validAttrRegxp);
+}
+var startsWithXML = new RegExp("^[Xx][Mm][Ll]");
+var startsWith = new RegExp("^([a-zA-Z]|_)[\\w\.\\-_:]*");
+
+function validateTagName(tagname){
+    if(util.doesMatch(tagname,startsWithXML)) return false;
+    else if(util.doesNotMatch(tagname,startsWith)) return false;
+    else return true;
+}
+
+
+
 },{"./util":2}]},{},[1])(1)
 });

package.json

 {
   "name": "fast-xml-parser",
-  "version": "2.8.3",
+  "version": "2.9.0",
   "description": "Validate XML or Parse XML to JS/JSON very fast without C/C++ based libraries",
@@ -5,0 +5,0 @@ "main": "./bin/parser.js",

README.md

@@ -91,3 +91,3 @@ # [fast-xml-parser](https://www.npmjs.com/package/fast-xml-parser)
 * Parser doesn't check if the XML is valid or not. If the XML is not valid you may get invalid result. So you can call the validator function first to check the structure.
-* This is based on JS regular expression engine. So due to it's limitation fast-xml-parser face performance issue when it process XML string(data) which is very large like 10mb or more. (I'll look into this as soon as I get some free time)
+* This is based on JS regular expression engine. So due to it's limitation fast-xml-parser face performance issue when it process XML string(data) which is very large like 10mb or more. (I'll look into this as soon as I get some free time). **UPDATE**: from v2.9.0, I have rewritten the validator code. So that validator can handle large files as well. I have tested it up to 98mb xml file. I have some more ideas to increase the speed. And I'll work whenever I get the time.
 
@@ -94,0 +94,0 @@ Report an issue or request for a feature [here](https://github.com/NaturalIntelligence/fast-xml-parser/issues)

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

204484

increased by3.41%

Lines of code

909

increased by29.3%

No dependency changes