barthélemy","saint helena","ascension and tristan da cunha","Ascension and tristan da cunha","saint kitts and nevis","saint lucia","saint martin","saint pierre and miquelon","saint vincent and the grenadines","samoa","san marino","sao tome and principe","saudi arabia","senegal","serbia","seychelles","sierra leone","singapore","sint maarten","slovakia","slovenia","solomon islands","somalia","south africa","south georgia and the south sandwich islands","south sudan","spain","sri lanka","sudan","suriname","svalbard...

0656..0658    ; valid                                  # 4.0  ARABIC SUBSCRIPT ALEF..ARABIC MARK NOON GHUNNA
0659..065E    ; valid                                  # 4.1  ARABIC ZWARAKAY..ARABIC FATHA WITH TWO DOTS
065F          ; valid                                  # 6.0  ARABIC WAVY HAMZA BELOW
0660..0669    ; valid                                  # 1.1  ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/tr/stopwords.txt
acaba
altmış
altı
ama
ancak
arada
aslında
ayrıca
bana
bazı
belki
ben
benden
beni
benim
beri
beş
bile
bin
bir
birçok
biri
birkaç
birkez
birşey
birşeyi
biz
bize
bizden
bizi
bizim
böyle
böylece
bu
buna
bunda
bundan
bunlar

          "type":       "keyword_marker",
          "keywords": ["สวัสดี", "โลก", "ค้นหา"]
        },
        "turkish_stop": {
          "type":       "stop",

          "type":       "keyword_marker",
          "keywords": ["สวัสดี", "โลก", "ค้นหา"]
        },
        "turkish_stop": {
          "type":       "stop",

рф

// xn--wgbl6a ("Qatar", Arabic) : QA
// http://www.ict.gov.qa/
قطر

// xn--mgberp4a5d4ar ("AlSaudiah", Arabic) : SA
// http://www.nic.net.sa/
السعودية

// xn--mgberp4a5d4a87g ("AlSaudiah", Arabic, variant)  : SA
السعودیة

// xn--mgbqly7c0a67fbc ("AlSaudiah", Arabic, variant) : SA
السعودیۃ

// xn--mgbqly7cvafr ("AlSaudiah", Arabic, variant) : SA
السعوديه

adanya
adalah
adapun
agak
agaknya
agar
akan
akankah
akhirnya
aku
akulah
amat
amatlah
anda
andalah
antar
diantaranya
antara
antaranya
diantara
apa
apaan
mengapa
apabila
apakah
apalagi
apatah
atau
ataukah
ataupun
bagai
bagaikan
sebagai
sebagainya
bagaimana
bagaimanapun
sebagaimana
bagaimanakah
bagi
bahkan
bahwa
bahwasanya
sebaliknya

import kotlin.test.Test
import kotlin.test.assertEquals
import kotlin.test.assertNull

class PunycodeTest {
  /** https://datatracker.ietf.org/doc/html/rfc3492#section-7.1 */
  @Test fun rfc3492Samples() {
    // (A) Arabic (Egyptian)
    testEncodeDecode(
      unicode = "ليهمابتكلموشعربي؟",
      punycode = "xn--egbpdaj6bu4bxfgehfvwxn",
    )

    // (B) Chinese (simplified)
    testEncodeDecode(
      unicode = "他们为什么不说中文",

                        <div class="card-header">
                            <h3 class="card-title">
                                <a aria-hidden="true" href="${contextPath}/admin/storage/">
                                    <i class="fas fa-database fa-fw"
                                       aria-hidden="true"></i>${f:h(bucket)}
                                </a>

				<div id="content" class="container">
					<div class="navbar-brand"></div>
					<button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar"
							aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
						<span class="navbar-toggler-icon"></span>
					</button>
					<div class="collapse navbar-collapse" id="navbar">
						<div class="me-auto"></div>