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

   202C; POP DIRECTIONAL FORMATTING
   202D; LEFT-TO-RIGHT OVERRIDE
   202E; RIGHT-TO-LEFT OVERRIDE
   206A; INHIBIT SYMMETRIC SWAPPING
   206B; ACTIVATE SYMMETRIC SWAPPING
   206C; INHIBIT ARABIC FORM SHAPING
   206D; ACTIVATE ARABIC FORM SHAPING
   206E; NATIONAL DIGIT SHAPES

        }
      },
      "analyzer": {
        "arabic_analyzer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "truncate20_filter",
            "lowercase",
            "arabic_stop",
            "arabic_normalization",
            "arabic_keywords",
            "arabic_override",
            "arabic_stemmer"
          ]
        },

   0080-009F; [CONTROL CHARACTERS]
   06DD; ARABIC END OF AYAH
   070F; SYRIAC ABBREVIATION MARK
   180E; MONGOLIAN VOWEL SEPARATOR
   200C; ZERO WIDTH NON-JOINER
   200D; ZERO WIDTH JOINER
   2028; LINE SEPARATOR
   2029; PARAGRAPH SEPARATOR
   2060; WORD JOINER
   2061; FUNCTION APPLICATION
   2062; INVISIBLE TIMES
   2063; INVISIBLE SEPARATOR
   206A-206F; [CONTROL CHARACTERS]
   FEFF; ZERO WIDTH NO-BREAK SPACE

      },
      "contents_reading_analyzer_ar" : {
        "type" : "custom",
        "tokenizer" : "standard",
        "filter" : ["lowercase", "stopword_en_filter", "content_length_filter", "limit_token_count_filter", "arabic_stop", "arabic_normalization", "arabic_keywords"]
      },
      "reading_analyzer_bg" : {

      },
      "contents_reading_analyzer_ar" : {
        "type" : "custom",
        "tokenizer" : "standard",
        "filter" : ["lowercase", "stopword_en_filter", "content_length_filter", "limit_token_count_filter", "arabic_stop", "arabic_normalization", "arabic_keywords"]
      },
      "reading_analyzer_bg" : {

      },
      "contents_reading_analyzer_ar" : {
        "type" : "custom",
        "tokenizer" : "standard",
        "filter" : ["lowercase", "stopword_en_filter", "content_length_filter", "limit_token_count_filter", "arabic_stop", "arabic_normalization", "arabic_keywords"]
      },
      "reading_analyzer_bg" : {

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

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",