YAML-zu-XML-Konverter

import yaml from 'js-yaml';
import { XMLBuilder } from 'fast-xml-parser';

// load() uses the default schema, which constructs no JavaScript types.
// Do not swap in js-yaml's extended schema for untrusted input.
const docs = [];
yaml.loadAll(yamlSource, (d) => docs.push(d));

if (docs.length === 0) throw new Error('The YAML document is empty.');
// XML has one root; a multi-document stream needs wrapping, not truncating.
let data = docs.length > 1 ? { documents: { document: docs } } : docs[0];

if (data === null || typeof data !== 'object' || Array.isArray(data)
    || Object.keys(data).length !== 1) {
  data = { root: data };
}

const builder = new XMLBuilder({
  ignoreAttributes: false,
  attributeNamePrefix: '@_',
  textNodeName: '#text',
  format: true,
  indentBy: '  ',
  suppressEmptyNode: true,
});

console.log('<?xml version="1.0" encoding="UTF-8"?>');
console.log(builder.build(data));

// XMLBuilder does not sanitise names. A YAML key of "2024 total" is written
// verbatim and the result will not parse, so validate before you ship it.

import re
import yaml
import xmltodict


def legal_name(key):
    """Replace illegal characters rather than stripping them, so distinct
    keys stay distinct. Prefix a leading digit."""
    name = re.sub(r'[^\w.\-:]', '_', str(key), flags=re.UNICODE)
    return name if re.match(r'^[A-Za-z_:]', name) else '_' + name


def sanitise(node):
    if isinstance(node, dict):
        return {legal_name(k): sanitise(v) for k, v in node.items()}
    if isinstance(node, list):
        return [sanitise(v) for v in node]
    if isinstance(node, bool):
        return 'true' if node else 'false'
    return node if node is None else str(node)


# safe_load, never load: yaml.load with the default Loader will construct
# arbitrary Python objects from !!python tags in the document.
docs = [d for d in yaml.safe_load_all(yaml_source) if d is not None]
if not docs:
    raise SystemExit('The YAML document is empty.')

data = {'documents': {'document': docs}} if len(docs) > 1 else docs[0]
if not isinstance(data, dict) or len(data) != 1:
    data = {'root': data}

print(xmltodict.unparse(sanitise(data), pretty=True, indent='  ',
                        full_document=True))

# PyYAML applies the YAML 1.1 resolver, so an unquoted no is False here and
# a string in js-yaml. Quote anything whose type you care about.

import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.SerializationFeature;
import com.fasterxml.jackson.dataformat.xml.XmlMapper;
import com.fasterxml.jackson.dataformat.yaml.YAMLMapper;

// Jackson's YAML module wraps SnakeYAML but binds only to JsonNode and to
// classes you name, so the SnakeYAML deserialisation gadget problem
// (CVE-2022-1471, the default Constructor instantiating arbitrary types)
// is not reachable through this API. Using SnakeYAML directly, construct it
// as: new Yaml(new SafeConstructor(new LoaderOptions()))
JsonNode tree = new YAMLMapper().readTree(yamlSource);

XmlMapper xml = new XmlMapper();
xml.enable(SerializationFeature.INDENT_OUTPUT);

String out = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
    + xml.writer().withRootName("root").writeValueAsString(tree);

// readTree reads the first document only. For a multi-document stream use
// new YAMLMapper().readerFor(JsonNode.class).readValues(yamlSource)
// and wrap the results yourself.

using Newtonsoft.Json;
using YamlDotNet.Serialization;

// YamlDotNet's Deserializer binds only to types you name and does not
// resolve arbitrary .NET types from tags in the document.
var yaml = new DeserializerBuilder().Build();
object? tree = yaml.Deserialize<object>(new StringReader(yamlSource));

if (tree is null) throw new InvalidOperationException("The YAML is empty.");

// Round-trip through JSON so Json.NET can do the XML writing, including the
// escaping. The second argument names the root, which YAML does not supply
// and XML requires.
string json = JsonConvert.SerializeObject(tree);
var document = JsonConvert.DeserializeXmlNode(json, "root")
    ?? throw new InvalidOperationException("Nothing to write.");

var settings = new System.Xml.XmlWriterSettings { Indent = true, IndentChars = "  " };
using var writer = System.Xml.XmlWriter.Create(Console.Out, settings);
document.Save(writer);

// Json.NET will not sanitise names: a YAML key of "2024 total" throws
// XmlException when the node is created. Rewrite keys before this point.

<?php
use Symfony\Component\Yaml\Yaml;

// Symfony's parser never instantiates PHP objects unless you pass
// PARSE_OBJECT or PARSE_OBJECT_FOR_MAP. Do not pass either for input you did
// not write. The ext-yaml alternative, yaml_parse(), is governed by the
// yaml.decode_php ini setting, which is off by default; check it.
$data = Yaml::parse($source, Yaml::PARSE_EXCEPTION_ON_INVALID_TYPE);

function legal_name(string $key): string {
    $name = preg_replace('/[^\w.\-:]/u', '_', $key);
    return preg_match('/^[A-Za-z_:]/', $name) ? $name : '_' . $name;
}

function write_node(XMLWriter $w, string $name, mixed $value): void {
    if (is_array($value) && array_is_list($value)) {
        foreach ($value as $v) write_node($w, $name, $v);   // repeat, no wrapper
        return;
    }
    $w->startElement(legal_name($name));
    if (is_array($value)) {
        foreach ($value as $k => $v) write_node($w, (string) $k, $v);
    } elseif (is_bool($value)) {
        $w->text($value ? 'true' : 'false');
    } elseif ($value !== null) {
        $w->text((string) $value);
    }
    $w->endElement();
}

$single = count($data) === 1;
$w = new XMLWriter();
$w->openMemory();
$w->setIndent(true);
$w->setIndentString('  ');
$w->startDocument('1.0', 'UTF-8');
write_node($w, $single ? (string) array_key_first($data) : 'root',
               $single ? reset($data) : $data);
$w->endDocument();
echo $w->outputMemory();

# yq v4 (Mike Farah) converts directly.
yq -p=yaml -o=xml '.' config.yaml

# yq writes no XML declaration and no wrapper, so a multi-key document
# produces several roots. Wrap it first:
yq -p=yaml -o=xml '{"root": .}' config.yaml

# A multi-document stream needs collecting into one root explicitly, or yq
# emits one XML fragment per document:
yq ea -p=yaml -o=xml '{"documents": {"document": [.]}}' manifests.yaml

# Always check the result. yq does not sanitise element names, so a key with
# a space in it produces XML that will not parse:
yq -p=yaml -o=xml '{"root": .}' config.yaml | xmllint --noout --nonet -