xml-twig 1.3.7 → 1.3.9

package/README.md

@@ -9,7 +9,7 @@ When you need to read a XML file, then you have two principles:
 
 * The **Document Object Model (DOM)** style. These parser read the entire XML document into memory. Usually they provide easy methods to navigate in the document tree or make modifications. 
 
-   DOM parsers are perfect for rather small files, for example configuration files or (X-)HTML pages. However, for bigger XML files you may run into memory limits.
+   DOM parsers are perfect for rather small files, for example configuration files or (X-)HTML pages. However, for bigger XML files you may run into memory limits. When you parse a XML-File as DOM, then the footprint in RAM can be easily 10-20 times the size of the raw XML-String. If the XML-File is greater than [Buffer.constants.MAX_STRING_LENGTH`](https://nodejs.org/api/buffer.html#bufferconstantsmax_string_length) (typically 512 MiB), then a DOM parser may throw error "Cannot create a string longer than 0x1fffffe8 characters".
 
 * The **stream** or **event** based parsers. These parser read the XML file "line by line". The biggest advantage of such a parser is, there is no limit in the size of the XML file. You can read XML files having a size of many terabytes, because you read always just a single node. 
 

package/package.json

@@ -5,7 +5,7 @@
   },
   "name": "xml-twig",
   "description": "Node module for processing huge XML documents in tree mode",
-  "version": "1.3.7",
+  "version": "1.3.9",
   "main": "twig.js",
   "directories": {
     "doc": "doc"

package/samples/dom-parsers.js

@@ -0,0 +1,108 @@
+var fs = require('fs');
+var xml = fs.readFileSync('../SwissProt.xml', 'utf8');
+
+console.log(`File Size: ${Math.round((xml.length / 1024 / 1024 + Number.EPSILON) * 100) / 100} MiB`);
+for (const [key, value] of Object.entries(process.memoryUsage())) 
+   console.log(`   Memory usage by ${key}, ${Math.round((value / 1024 / 1024 + Number.EPSILON) * 100) / 100} MiB`)
+
+/*
+File Size of dblp.xml: 127.66 MiB
+   Memory usage by rss, 290.71 MiB
+   Memory usage by heapTotal, 137.07 MiB
+   Memory usage by heapUsed, 135.74 MiB
+   Memory usage by external, 128.53 MiB
+   Memory usage by arrayBuffers, 0.02 MiB
+
+File Size of SwissProt.xml: 109.5 MiB
+   Memory usage by rss, 387.96 MiB
+   Memory usage by heapTotal, 257.09 MiB
+   Memory usage by heapUsed, 247.7 MiB
+   Memory usage by external, 110.37 MiB
+   Memory usage by arrayBuffers, 109.52 MiB
+*/
+
+
+/*
+const { XMLParser } = require("fast-xml-parser");
+let parser = new XMLParser();
+let obj = parser.parse(xml);
+for (const [key, value] of Object.entries(process.memoryUsage())) 
+   console.log(`   Memory usage by ${key}, ${Math.round((value / 1024 / 1024 + Number.EPSILON) * 100) / 100} MiB`)
+*/
+/*
+   Memory usage by rss, 1482.1 MiB
+   Memory usage by heapTotal, 1444.53 MiB
+   Memory usage by heapUsed, 1396.38 MiB
+   Memory usage by external, 0.87 MiB
+   Memory usage by arrayBuffers, 0.02 MiB
+*/
+
+/*
+const twig = require('../twig.js');
+let parser = twig.createParser([{ tag: twig.Root, function: rootHandler }], { method: 'expat' })
+let reader = fs.createReadStream(`../SwissProt.xml`);
+reader.pipe(parser);
+function rootHandler(elt) {
+   for (const [key, value] of Object.entries(process.memoryUsage())) 
+      console.log(`   Memory usage by ${key}, ${Math.round((value / 1024 / 1024 + Number.EPSILON) * 100) / 100} MiB`)
+}
+*/
+/*
+   Memory usage by rss, 8872.57 MiB
+   Memory usage by heapTotal, 8779.85 MiB
+   Memory usage by heapUsed, 8586.22 MiB
+   Memory usage by external, 1.15 MiB
+   Memory usage by arrayBuffers, 0.3 MiB
+*/
+
+
+/*
+const parse = require('xml-parser');
+let obj = parse(xml);
+for (const [key, value] of Object.entries(process.memoryUsage()))
+   console.log(`   Memory usage by ${key}, ${Math.round((value / 1024 / 1024 + Number.EPSILON) * 100) / 100} MiB`)
+/*
+Running for ages...
+*/
+
+
+/*
+const xml2js = require('xml2js');
+var parser = new xml2js.Parser();
+parser.parseString(xml, function (err, result) {
+   for (const [key, value] of Object.entries(process.memoryUsage()))
+      console.log(`   Memory usage by ${key}, ${Math.round((value / 1024 / 1024 + Number.EPSILON) * 100) / 100} MiB`)
+
+   console.log('Done');
+});
+*/
+/*
+   Memory usage by rss, 898.91 MiB
+   Memory usage by heapTotal, 863.84 MiB
+   Memory usage by heapUsed, 825.19 MiB
+   Memory usage by external, 0.87 MiB
+   Memory usage by arrayBuffers, 0.02 MiB
+*/
+/*
+const parser = require("xml-parse");
+var parsedXML = parser.parse(xml);
+for (const [key, value] of Object.entries(process.memoryUsage()))
+   console.log(`   Memory usage by ${key}, ${Math.round((value / 1024 / 1024 + Number.EPSILON) * 100) / 100} MiB`)
+// -> Uncaught RangeError RangeError: Maximum call stack size exceeded
+*/
+
+/*
+const { parseXml } = require('@rgrove/parse-xml');
+let r = parseXml(xml);
+for (const [key, value] of Object.entries(process.memoryUsage()))
+   console.log(`   Memory usage by ${key}, ${Math.round((value / 1024 / 1024 + Number.EPSILON) * 100) / 100} MiB`)
+*/
+/*
+   Memory usage by rss, 1943.94 MiB
+   Memory usage by heapTotal, 1903.21 MiB
+   Memory usage by heapUsed, 1854.36 MiB
+   Memory usage by external, 0.87 MiB
+   Memory usage by arrayBuffers, 0.02 MiB
+*/
+
+

package/twig.js

@@ -769,6 +769,14 @@ class Twig {
       return this.root().writer(true, true).output;
    };
 
+   /**
+   * Returns XML string of the element
+   * @returns {string} The XML-Element as string
+   */
+   toString = function () {
+      return this.writer(true).toString();
+   };
+
    /**
    * Internal recursive function used by `writer()`
    * @param {external:XMLWriter} xw - The writer object