XML을 JSON으로 변환

import { XMLParser } from 'fast-xml-parser';

const parser = new XMLParser({
  ignoreAttributes: false,       // default is true: attributes are DROPPED
  attributeNamePrefix: '@_',
  textNodeName: '#text',
  trimValues: true,
  parseTagValue: false,          // keep values as strings
  parseAttributeValue: false,
  processEntities: false,        // do not expand DOCTYPE-declared entities
  // FXP cannot know whether a tag repeats, so tell it which ones are lists.
  isArray: (name) => ['line', 'item', 'entry'].includes(name),
});

const json = parser.parse(xmlSource);

// fast-xml-parser never fetches anything over the network, so XXE is not
// reachable. It does expand entities declared in an internal DTD unless you
// set processEntities: false, so leave that off for untrusted input and cap
// the input size before parsing.

import json
import xmltodict

# disable_entities=True is the default in current xmltodict and blocks the
# expat entity-expansion attacks. Pass it explicitly so a downgrade of the
# dependency cannot silently re-enable them.
doc = xmltodict.parse(
    xml_source,
    disable_entities=True,
    attr_prefix='@_',
    cdata_key='#text',
    force_list=('line', 'item', 'entry'),   # the singleton fix
)

print(json.dumps(doc, indent=2, ensure_ascii=False))

# xmltodict returns dicts in document order, but that ordering has no meaning
# once serialised: JSON objects are unordered. Values are always strings.
# There is no coercion, which is the right default.

import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.fasterxml.jackson.dataformat.xml.XmlFactory;
import com.fasterxml.jackson.dataformat.xml.XmlMapper;
import javax.xml.stream.XMLInputFactory;

XMLInputFactory input = XMLInputFactory.newFactory();
// Neither of these is off by default. Both must be, for untrusted XML.
input.setProperty(XMLInputFactory.SUPPORT_DTD, false);
input.setProperty(XMLInputFactory.IS_SUPPORTING_EXTERNAL_ENTITIES, false);

XmlMapper xml = new XmlMapper(new XmlFactory(input));
JsonNode tree = xml.readTree(xmlSource);

String json = new ObjectMapper()
    .writerWithDefaultPrettyPrinter()
    .writeValueAsString(tree);

// Jackson's XML module merges attributes in with child elements: there is no
// prefix, so <user id="7"><id>8</id></user> loses one of the two. If your
// documents put data on attributes, bind to a class annotated with
// @JacksonXmlProperty(isAttribute = true) instead of reading a tree.

using System.Xml;
using Newtonsoft.Json;

var settings = new XmlReaderSettings
{
    DtdProcessing = DtdProcessing.Prohibit,
    XmlResolver = null,
    MaxCharactersFromEntities = 1024 * 1024,
    MaxCharactersInDocument = 20L * 1024 * 1024,
};

using var reader = XmlReader.Create(new StringReader(xmlSource), settings);
var document = new XmlDocument { XmlResolver = null };
document.Load(reader);

// omitRootObject: false keeps the root element as the outer key.
string json = JsonConvert.SerializeXmlNode(
    document, Newtonsoft.Json.Formatting.Indented, omitRootObject: false);

// Json.NET prefixes attributes with "@" and uses "#text" for text, close to
// the convention on this page. It has the singleton problem and no isArray
// hook: the only fix is a json:Array="true" attribute in the source XML,
// which you usually do not control.

<?php
libxml_use_internal_errors(true);

// LIBXML_NONET blocks network access for any DTD the document references.
// LIBXML_NOENT is deliberately NOT passed: it would substitute entities.
$xml = simplexml_load_string($source, 'SimpleXMLElement', LIBXML_NONET);

if ($xml === false) {
    foreach (libxml_get_errors() as $e) {
        fprintf(STDERR, "line %d col %d: %s\n", $e->line, $e->column, trim($e->message));
    }
    exit(1);
}

echo json_encode($xml, JSON_PRETTY_PRINT | JSON_UNESCAPED_SLASHES), "\n";

// Two things to know first. json_encode() puts attributes under an
// "@attributes" object, not a prefix. And when an element has both text and
// child elements, SimpleXML drops the text entirely: mixed content does not
// survive this route at all.

# yq v4 (Mike Farah) reads XML and writes JSON with no Python dependency.
yq -p=xml -o=json '.' document.xml

# Attributes are prefixed with + by default; match this page's convention:
yq -p=xml -o=json --xml-attribute-prefix='@_' '.' document.xml

# yq resolves nothing over the network. It also has the singleton problem and
# no per-tag array option, so a list of one comes back as a scalar. Normalise
# on the way into jq:
yq -p=xml -o=json '.' document.xml \
  | jq '.order.line |= (if type == "array" then . else [.] end)'