@depup/fast-xml-parser 5.5.6-depup.0

package/src/v6/XmlSpecialTagsReader.js

@@ -0,0 +1,111 @@
+import {readPiExp} from './XmlPartReader.js';
+
+export function readCdata(parser){
+  //<![ are already read till this point
+  let str = parser.source.readStr(6); //CDATA[
+  parser.source.updateBufferBoundary(6);
+
+  if(str !== "CDATA[") throw new Error(`Invalid CDATA expression at ${parser.source.line}:${parser.source.cols}`);
+
+  let text = parser.source.readUpto("]]>");
+  parser.outputBuilder.addCdata(text);
+}
+export function readPiTag(parser){
+  //<? are already read till this point
+  let tagExp = readPiExp(parser, "?>");
+  if(!tagExp) throw new Error("Invalid Pi Tag expression.");
+
+  if (tagExp.tagName === "?xml") {//TODO: test if tagName is just xml
+    parser.outputBuilder.addDeclaration();
+  } else {
+    parser.outputBuilder.addPi("?"+tagExp.tagName);
+  }
+}
+
+export function readComment(parser){
+  //<!- are already read till this point
+  let ch = parser.source.readCh();
+  if(ch !== "-") throw new Error(`Invalid comment expression at ${parser.source.line}:${parser.source.cols}`);
+
+  let text = parser.source.readUpto("-->");
+  parser.outputBuilder.addComment(text);
+}
+
+const DOCTYPE_tags = {
+  "EL":/^EMENT\s+([^\s>]+)\s+(ANY|EMPTY|\(.+\)\s*$)/m,
+  "AT":/^TLIST\s+[^\s]+\s+[^\s]+\s+[^\s]+\s+[^\s]+\s+$/m,
+  "NO":/^TATION.+$/m
+}
+export function readDocType(parser){
+  //<!D are already read till this point
+  let str = parser.source.readStr(6); //OCTYPE
+  parser.source.updateBufferBoundary(6);
+
+  if(str !== "OCTYPE") throw new Error(`Invalid DOCTYPE expression at ${parser.source.line}:${parser.source.cols}`);
+
+  let hasBody = false, lastch = "";
+
+  while(parser.source.canRead()){
+    //TODO: use readChAt like used in partReader
+    let ch = parser.source.readCh();
+    if(hasBody){
+      if (ch === '<') { //Determine the tag type
+        let str = parser.source.readStr(2);
+        parser.source.updateBufferBoundary(2);
+        if(str === "EN"){ //ENTITY
+          let str = parser.source.readStr(4);
+          parser.source.updateBufferBoundary(4);
+          if(str !== "TITY") throw new Error("Invalid DOCTYPE ENTITY expression");
+
+          registerEntity(parser);
+        }else if(str === "!-") {//comment
+          readComment(parser);
+        }else{ //ELEMENT, ATTLIST, NOTATION
+          let dTagExp = parser.source.readUpto(">");
+          const regx = DOCTYPE_tags[str];
+          if(regx){
+            const match = dTagExp.match(regx);
+            if(!match) throw new Error("Invalid DOCTYPE");
+          }else throw new Error("Invalid DOCTYPE");
+        }
+      }else if( ch === '>' && lastch === "]"){//end of doctype
+        return;  
+      }
+    }else if( ch === '>'){//end of doctype
+      return;
+    }else if( ch === '['){
+      hasBody = true;
+    }else{
+      lastch = ch;
+    }
+  }//End While loop
+
+}
+
+function registerEntity(parser){
+  //read Entity
+  let attrBoundary="";
+  let name ="", val ="";
+  while(source.canRead()){
+    let ch = source.readCh();
+
+    if(attrBoundary){
+      if (ch === attrBoundary){
+        val = text;
+        text = ""
+      }
+    }else if(ch === " " || ch === "\t"){
+      if(!name){
+        name = text.trimStart();
+        text = "";
+      }
+    }else if (ch === '"' || ch === "'") {//start of attrBoundary
+      attrBoundary = ch;
+    }else if(ch === ">"){
+      parser.entityParser.addExternalEntity(name,val);
+      return;
+    }else{
+      text+=ch;
+    }
+  }
+}

package/src/v6/inputSource/BufferSource.js

@@ -0,0 +1,116 @@
+const Constants = {
+  space: 32,
+  tab: 9
+}
+export default class BufferSource{
+  constructor(bytesArr){
+    this.line = 1;
+    this.cols = 0;
+    this.buffer = bytesArr;
+    this.startIndex = 0;
+  }
+
+
+
+  readCh() {
+    return String.fromCharCode(this.buffer[this.startIndex++]);
+  }
+
+  readChAt(index) {
+    return String.fromCharCode(this.buffer[this.startIndex+index]);
+  }
+
+  readStr(n,from){
+    if(typeof from === "undefined") from = this.startIndex;
+    return this.buffer.slice(from, from + n).toString();
+  }
+
+  readUpto(stopStr) {
+    const inputLength = this.buffer.length;
+    const stopLength = stopStr.length;
+    const stopBuffer = Buffer.from(stopStr);
+
+    for (let i = this.startIndex; i < inputLength; i++) {
+        let match = true;
+        for (let j = 0; j < stopLength; j++) {
+            if (this.buffer[i + j] !== stopBuffer[j]) {
+                match = false;
+                break;
+            }
+        }
+
+        if (match) {
+            const result = this.buffer.slice(this.startIndex, i).toString();
+            this.startIndex = i + stopLength;
+            return result;
+        }
+    }
+
+    throw new Error(`Unexpected end of source. Reading '${stopStr}'`);
+}
+
+readUptoCloseTag(stopStr) { //stopStr: "</tagname"
+    const inputLength = this.buffer.length;
+    const stopLength = stopStr.length;
+    const stopBuffer = Buffer.from(stopStr);
+    let stopIndex = 0;
+    //0: non-matching, 1: matching stop string, 2: matching closing
+    let match = 0;
+
+    for (let i = this.startIndex; i < inputLength; i++) {
+        if(match === 1){//initial part matched
+            if(stopIndex === 0) stopIndex = i;
+            if(this.buffer[i] === Constants.space || this.buffer[i] === Constants.tab) continue;
+            else if(this.buffer[i] === '>'){ //TODO: if it should be equivalent ASCII
+                match = 2;
+                //tag boundary found
+                // this.startIndex
+            }
+        }else{
+            match = 1;
+            for (let j = 0; j < stopLength; j++) {
+                if (this.buffer[i + j] !== stopBuffer[j]) {
+                    match = 0;
+                    break;
+                }
+            }
+        }
+        if (match === 2) {//matched closing part
+            const result = this.buffer.slice(this.startIndex, stopIndex - 1 ).toString();
+            this.startIndex = i + 1;
+            return result;
+        }
+    }
+
+    throw new Error(`Unexpected end of source. Reading '${stopStr}'`);
+}
+
+  readFromBuffer(n, shouldUpdate) {
+    let ch;
+    if (n === 1) {
+      ch = this.buffer[this.startIndex];
+      if (ch === 10) {
+        this.line++;
+        this.cols = 1;
+      } else {
+        this.cols++;
+      }
+      ch = String.fromCharCode(ch);
+    } else {
+      this.cols += n;
+      ch = this.buffer.slice(this.startIndex, this.startIndex + n).toString();
+    }
+    if (shouldUpdate) this.updateBuffer(n);
+    return ch;
+  }
+
+  updateBufferBoundary(n = 1) { //n: number of characters read
+    this.startIndex += n;
+  }
+
+  canRead(n){
+    n = n || this.startIndex;
+    return this.buffer.length - n + 1 > 0;
+  }
+  
+}

package/src/v6/inputSource/StringSource.js

@@ -0,0 +1,121 @@
+const whiteSpaces = [" ", "\n", "\t"];
+
+
+export default class StringSource{
+  constructor(str){
+    this.line = 1;
+    this.cols = 0;
+    this.buffer = str;
+    //a boundary pointer to indicate where from the buffer dat should be read
+    // data before this pointer can be deleted to free the memory
+    this.startIndex = 0;
+  }
+
+  readCh() {
+    return this.buffer[this.startIndex++];
+  }
+
+  readChAt(index) {
+    return this.buffer[this.startIndex+index];
+  }
+
+  readStr(n,from){
+    if(typeof from === "undefined") from = this.startIndex;
+    return this.buffer.substring(from, from + n);
+  }
+
+  readUpto(stopStr) {
+    const inputLength = this.buffer.length;
+    const stopLength = stopStr.length;
+
+    for (let i = this.startIndex; i < inputLength; i++) {
+      let match = true;
+      for (let j = 0; j < stopLength; j++) {
+        if (this.buffer[i + j] !== stopStr[j]) {
+          match = false;
+          break;
+        }
+      }
+
+      if (match) {
+        const result = this.buffer.substring(this.startIndex, i);
+        this.startIndex = i + stopLength;
+        return result;
+      }
+    }
+
+    throw new Error(`Unexpected end of source. Reading '${stopStr}'`);
+  }
+
+  readUptoCloseTag(stopStr) { //stopStr: "</tagname"
+    const inputLength = this.buffer.length;
+    const stopLength = stopStr.length;
+    let stopIndex = 0;
+    //0: non-matching, 1: matching stop string, 2: matching closing
+    let match = 0;
+
+    for (let i = this.startIndex; i < inputLength; i++) {
+      if(match === 1){//initial part matched
+        if(stopIndex === 0) stopIndex = i;
+        if(this.buffer[i] === ' ' || this.buffer[i] === '\t') continue;
+        else if(this.buffer[i] === '>'){
+          match = 2;
+          //tag boundary found
+          // this.startIndex
+        }
+      }else{
+        match = 1;
+        for (let j = 0; j < stopLength; j++) {
+          if (this.buffer[i + j] !== stopStr[j]) {
+            match = 0;
+            break;
+          }
+        }
+      }
+      if (match === 2) {//matched closing part
+        const result = this.buffer.substring(this.startIndex, stopIndex - 1 );
+        this.startIndex = i + 1;
+        return result;
+      }
+    }
+
+    throw new Error(`Unexpected end of source. Reading '${stopStr}'`);
+  }
+
+  readFromBuffer(n, updateIndex){
+    let ch;
+    if(n===1){
+      ch = this.buffer[this.startIndex];
+      // if(ch === "\n") {
+      //   this.line++;
+      //   this.cols = 1;
+      // }else{
+      //   this.cols++;
+      // }
+    }else{
+      ch = this.buffer.substring(this.startIndex, this.startIndex + n);
+      // if("".indexOf("\n") !== -1){
+      //   //TODO: handle the scenario when there are multiple lines
+      //   //TODO: col should be set to number of chars after last '\n'
+      //   // this.cols = 1;
+      // }else{
+      //   this.cols += n;
+
+      // }
+    }
+    if(updateIndex) this.updateBufferBoundary(n);
+    return ch;
+  }
+
+  //TODO: rename to updateBufferReadIndex
+  
+  updateBufferBoundary(n = 1) { //n: number of characters read
+    this.startIndex += n;
+  }
+
+  canRead(n){
+    n = n || this.startIndex;
+    return this.buffer.length - n + 1 > 0;
+  }
+  
+}

package/src/v6/valueParsers/EntitiesParser.js

@@ -0,0 +1,105 @@
+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.fromCodePoint(Number.parseInt(str, 10)) },
+  "num_hex": { regex: /&#x([0-9a-fA-F]{1,6});/g, val: (_, str) => String.fromCodePoint(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/valueParsers/booleanParser.js

@@ -0,0 +1,22 @@
+export default class boolParser{
+    constructor(trueList, falseList){
+        if(trueList)
+            this.trueList = trueList;
+        else
+            this.trueList = ["true"];
+        
+        if(falseList)
+            this.falseList = falseList;
+        else
+            this.falseList = ["false"];
+    }
+    parse(val){
+        if (typeof val === 'string') {
+            //TODO: performance: don't convert
+            const temp = val.toLowerCase();
+            if(this.trueList.indexOf(temp) !== -1) return true;
+            else if(this.falseList.indexOf(temp) !== -1 ) return false;
+        }
+        return val;
+    }
+}

package/src/v6/valueParsers/booleanParserExt.js

@@ -0,0 +1,19 @@
+export default function boolParserExt(val){
+    if(isArray(val)){
+        for (let i = 0; i < val.length; i++) {
+            val[i] = parse(val[i])
+        }
+    }else{
+        val = parse(val)
+    }
+    return val;
+}
+
+function parse(val){
+    if (typeof val === 'string') {
+        const temp = val.toLowerCase();
+        if(temp === 'true' || temp ==="yes" || temp==="1") return true;
+        else if(temp === 'false' || temp ==="no" || temp==="0") return false;
+    }
+    return val;
+}

package/src/v6/valueParsers/currency.js

@@ -0,0 +1,38 @@
+const defaultOptions = {
+    maxLength: 200,
+    // locale: "en-IN"
+}
+const localeMap = {
+    "$":"en-US",
+    "€":"de-DE",
+    "£":"en-GB",
+    "¥":"ja-JP",
+    "₹":"en-IN",
+}
+const sign = "(?:-|\+)?";
+const digitsAndSeparator = "(?:\d+|\d{1,3}(?:,\d{3})+)";
+const decimalPart = "(?:\.\d{1,2})?";
+const symbol = "(?:\$|€|¥|₹)?";
+
+const currencyCheckRegex = /^\s*(?:-|\+)?(?:\d+|\d{1,3}(?:,\d{3})+)?(?:\.\d{1,2})?\s*(?:\$|€|¥|₹)?\s*$/u;
+
+export default class CurrencyParser{
+    constructor(options){
+        this.options = options || defaultOptions;
+    }
+    parse(val){
+        if (typeof val === 'string' && val.length <= this.options.maxLength) {
+            if(val.indexOf(",,") !== -1 && val.indexOf(".." !== -1)){
+                const match = val.match(currencyCheckRegex);
+                if(match){
+                    const locale = this.options.locale || localeMap[match[2]||match[5]||"₹"];
+                    const formatter = new Intl.NumberFormat(locale)
+                    val = val.replace(/[^0-9,.]/g, '').trim();
+                    val = Number(val.replace(formatter.format(1000)[1], ''));
+                }
+            }
+        }
+        return val;
+    }
+}
+CurrencyParser.defaultOptions = defaultOptions;

package/src/v6/valueParsers/join.js

@@ -0,0 +1,13 @@
+/**
+ * 
+ * @param {array} val 
+ * @param {string} by 
+ * @returns 
+ */
+export default function join(val, by=" "){
+    if(isArray(val)){
+        val.join(by)
+    }
+    return val;
+}
+

package/src/v6/valueParsers/number.js

@@ -0,0 +1,14 @@
+import toNumber from "strnum";
+
+
+export default class numParser{
+    constructor(options){
+        this.options = options;
+    }
+    parse(val){
+        if (typeof val === 'string') {
+            val = toNumber(val,this.options);
+        }
+        return val;
+    }
+}

package/src/v6/valueParsers/trim.js

@@ -0,0 +1,6 @@
+export default class trimmer{
+    parse(val){
+        if(typeof val === "string") return val.trim();
+        else return val;
+    }
+}