interscript-maps 2.4.3 → 2.5.0

data/maps/bgnpcgn-bul-Cyrl-Latn-1952.isc

@@ -0,0 +1,213 @@
+system "BGN-PCGN:bul-Cyrl:Latn:1952" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1952
+  language iso-639-2:bul
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Bulgarian (1952)
+  url https://libraries.ucsd.edu/bib/fed/USBGN_romanization.pdf
+  creation_date 1945
+  confirmation_date 1952
+  description {    This system was adopted by the BGN in 1949 and by the PCGN in 1952. It
+    reflects the much simplified Bulgarian orthography as officially revised in
+    February 1945. The Bulgarian alphabet contains all of the characters present
+    in the Russian alphabet with the exception of ё, ы, and э. Notes 1, 2, and 3
+    are applicable to sources predating the orthographic reform of 1945.
+  }
+
+  notes {
+    note "In modern Bulgarian orthography, the character ъ, does not occur in\n word-final position. It should be omitted in romanization when found in\n word-final position on older sources"
+    note "The obsolete character ѫ, which was replaced by ъ in 1945, should be romanized ŭ"
+    note "The obsolete character ѣ, replaced in 1945 by е or я according to local\n pronunciation, should be romanized as e or ya, accordingly, if the\n pronunciation is known; otherwise, as ye"
+    note "The character sequence тс may be romanized t·s in order to differentiate\n that romanization from the regularly occurring digraph ts, which represents\n the character ц"
+  }
+}
+
+tests {
+   "София" ->  "Sofiya"
+   "София-Град" ->  "Sofiya-Grad"
+   "България" ->  "Bŭlgariya"
+}
+
+stage main {
+  # RULES
+  # note[1]
+  sub {
+    from "\u042a"
+    to ""
+    after boundary
+  }
+  sub {
+    from "\u044a"
+    to ""
+    after boundary
+  }
+  # note[4]
+  parallel {
+    sub "ТС" "T·S"
+    sub "Тс" "T·s"
+    sub "тс" "t·s"
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0416" "Zh"
+    sub {
+    from "\u0416"
+    to "ZH"
+    after any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub {
+    from "\u0416"
+    to "ZH"
+    before any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0419" "Y"
+    sub "\u041a" "K"
+    sub "\u041b" "L"
+    sub "\u041c" "M"
+    sub "\u041d" "N"
+    sub "\u041e" "O"
+    sub "\u041f" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub {
+    from "\u0425"
+    to "KH"
+    after any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub {
+    from "\u0425"
+    to "KH"
+    before any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+
+    sub "\u0426" "Ts"
+    sub {
+    from "\u0426"
+    to "TS"
+    after any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub {
+    from "\u0426"
+    to "TS"
+    before any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+
+    sub "\u0427" "Ch"
+    sub {
+    from "\u0427"
+    to "CH"
+    after any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub {
+    from "\u0427"
+    to "CH"
+    before any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+
+    sub "\u0428" "Sh"
+    sub {
+    from "\u0428"
+    to "SH"
+    after any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub {
+    from "\u0428"
+    to "SH"
+    before any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+
+    sub "\u0429" "Sht"
+    sub {
+    from "\u0429"
+    to "SHT"
+    after any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub {
+    from "\u0429"
+    to "SHT"
+    before any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+
+    sub "\u042a" "Ŭ"
+    sub "\u042c" "\\'"
+    sub "\u042e" "Yu"
+    sub {
+    from "\u042e"
+    to "YU"
+    after any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub {
+    from "\u042e"
+    to "YU"
+    before any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+
+    sub "\u042f" "Ya"
+    sub {
+    from "\u042f"
+    to "YA"
+    after any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+    sub {
+    from "\u042f"
+    to "YA"
+    before any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+  }
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0436" "zh"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043a" "k"
+    sub "\u043b" "l"
+    sub "\u043c" "m"
+    sub "\u043d" "n"
+    sub "\u043e" "o"
+    sub "\u043f" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u0449" "sht"
+    sub "\u044a" "ŭ"
+    sub "\u044c" "\\'"
+    sub "\u044e" "yu"
+    sub "\u044f" "ya"
+
+    # note 2
+    sub "\u046A" "Ŭ"
+    sub "\u046B" "ŭ"
+
+    # note[3]
+    sub "\u0462" "Ye"
+    sub "\u0463" "ye"
+  }
+}
+}

data/maps/bgnpcgn-bul-Cyrl-Latn-2013.isc

@@ -0,0 +1,52 @@
+system "BGN-PCGN:bul-Cyrl:Latn:2013" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2013
+  language iso-639-2:bul
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Bulgarian (2013 Agreement)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811509/ROMANIZATION_OF_BULGARIAN.pdf
+  creation_date 2013
+  confirmation_date 2019-06
+  description {    This system reflects the Bulgarian national system officially adopted
+    by state decree in March 2009. It was adopted by BGN and PCGN in 2013,
+    replacing the BGN/PCGN system of 1952.
+  }
+
+  notes {
+    note "When in final position, “ия” is romanized as “ia” (e.g., София = Sofia; София-Град= Sofia-Grad)."
+    note "An exception to the romanization system is allowed for the name of the state. Thus, България is romanized as Bulgaria."
+    note "The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+   "София" ->  "Sofia"
+   "София-Град" ->  "Sofia-Grad"
+   "България" ->  "Bulgaria"
+}
+
+dependency "bgnpcgn-bul-Cyrl-Latn-1952" as cyrllatn
+
+
+stage main {
+  # RULES
+  sub "България" "Bulgaria"
+  sub {
+    from "\u042f"
+    to "A"
+    before "\u0418"
+    after boundary
+  }
+  sub {
+    from "\u044f"
+    to "a"
+    before "\u0438"
+    after boundary
+  }
+
+  run  map.cyrllatn.stage.main
+}
+}

data/maps/bgnpcgn-che-Cyrl-Latn-2008.isc

@@ -0,0 +1,183 @@
+system "BGN-PCGN:che-Cyrl:Latn:2008" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2008
+  language iso-639-2:che
+  source_script Cyrl
+  destination_script Latn
+  name Table of Correspondences for Chechen (Cyrillic-Roman) (2008 Agreement)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
+  creation_date 2008
+  confirmation_date 2019-07
+  description {    Chechen is an official language within Chechnya, one of the republics of the Russian Federation.
+    It will normally be encountered in Cyrillic script, in which case it should be romanized by means of
+    the Cyrillic-Roman table of correspondences given below.
+  }
+
+  notes {
+    note "The letter ə is used to represent short a; a is used for long a."
+    note "Ye is used word- and syllable-initially. This Cyrillic letter may be encountered as the ligature ie in Chechen-Roman sources."
+    note "This character occurs only in loan words."
+    note "q in the combination ккх (qq) and q̇in the combination ккъ (q̇q̇)"
+    note "ŋ when preceding vowel is nasalized."
+    note "This Cyrillic letter may be encountered as the ligature ꭣ [U+AB63] or the diphthong oa in Chechen Roman sources."
+    note "Unless in the combinations гӀ, кӀ, пӀ, тӀ, хӀ, цӀ and чӀ."
+    note "      An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the\n      unmodified letters of the basic Roman script is:\n\n      All apostrophes appearing in romanization are U+2019\n\n          Ə (U+018F)       ə (U+0259)\n          Ä (U+00C4)       ä (U+00E4)\n          Ġ (U+0047+0307)  ġ (U+0067+0307)\n          Z̵ (U+005A+0335)  z̵ (U+007A+0335)\n          Q̇ (U+0051+0307)  q̇ (U+0071+0307)\n          Ŋ (U+014A)       ŋ (U+014B)\n          Ö (U+00D6)       ö (U+00F6)\n          Ü (U+00DC)       ü (U+00FC)\n          Ẋ (U+0058+0307)  ẋ (U+0078+0307)\n          Ċ (U+0043+0307)  ċ (U0063+0307)\n          Ç (U+00C7)       ç (U+00E7)\n          Ç̇ (U+00C7+0307)  ç̇ (U+00E7+0307)\n          Ş (U+015E)       ş (U+015F)"
+
+    note "The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used"
+  }
+}
+
+tests {
+   "кӏант" ->  "khant"
+   "зуда" ->  "zuda"
+   "пхьагал" ->  "pẋagal"
+   "наж" ->  "naz̵"
+   "мангал" ->  "mangal"
+   "Ӏаж" ->  "Jaz̵"
+   "Нохчийн Википеди" ->  "Noxçiyn Vikipedi"
+   "сагӏадаккхар" ->  "saġadaqqar"
+   "йеза" ->  "yeza"
+   "еара" ->  "yeara"
+   "елха" ->  "yelxa"
+}
+
+stage main {
+
+  # RULES
+  # note[2]
+  sub {
+    from boundary + "\u0415"
+    to "Ye"
+    not_before boundary + "\u2019"
+  }
+  sub {
+    from boundary + "\u0435"
+    to "ye"
+    not_before boundary + "\u2019"
+  }
+  # note[4]
+  sub "\u043A\u043A\u0445" "qq"
+  sub "\u043A\u043A\u042A" "q̇q̇"
+  sub "\u041A\u041A\u0445" "QQ"
+  sub "\u041A\u041A\u042A" "Q̇Q̇"
+
+
+  # CHARACTERS
+  parallel {
+    sub {
+    from "\u0410"
+    to any(["A", "Ə"])
+  }
+    sub "\u0410\u044C" "Ä"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0413\u04C0" "Ġ"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0401" "Yo"
+    sub "\u0416" "Z̵"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u042B" "Y"
+    sub "\u041A" "K"
+    sub "\u041A\u0445" "Q"
+    sub "\u041A\u044A" "Q̇"
+    sub "\u041A\u04C0" "Kh"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub {
+    from "\u041D"
+    to any(["N", "Ŋ"])
+  }
+    sub "\u041E" "O"
+    sub "\u041E\u044C" "Ö"
+    sub "\u041F" "P"
+    sub "\u041F\u04C0" "Ph"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0422\u04C0" "Th"
+    sub "\u0423" "U"
+    sub "\u0423\u044C" "Ü"
+    sub "\u0424" "F"
+    sub "\u0425" "X"
+    sub "\u0425\u044C" "Ẋ"
+    sub "\u0425\u04C0" "H"
+    sub "\u04B8" "C"
+    sub "\u04B8\u04C0" "Ċ"
+    sub "\u0427" "Ç"
+    sub "\u0427\u04C0" "Ç̇"
+    sub "\u0428" "Ş"
+    sub "\u0429" "ŞÇ"
+    sub "\u042A" "’"
+    sub "\u042B" "Y"
+    sub "\u042C" ""
+    sub "\u042D" "E"
+    sub "\u042E" "Yu"
+    sub "\u042E\u044C" "Yü"
+    sub "\u042F" "Ya"
+    sub "\u042F\u044C" "Yä"
+    sub "\u04C0" "J"
+
+    sub {
+    from "\u0430"
+    to any(["a", "ə"])
+  }
+    sub "\u0430\u044C" "ä"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0433\u04CF" "ġ"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0451" "yo"
+    sub "\u0436" "z̵"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u043A\u0445" "q"
+    sub "\u043A\u044A" "q̇"
+    sub "\u043A\u04CF" "kh"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub {
+    from "\u043D"
+    to any(["n", "ŋ"])
+  }
+    sub "\u043E" "o"
+    sub "\u043E\u044C" "ö"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0442\u04CF" "th"
+    sub "\u0443" "u"
+    sub "\u0443\u044C" "ü"
+    sub "\u0444" "f"
+    sub "\u0445" "x"
+    sub "\u0445\u044C" "ẋ"
+    sub "\u0445\u04CF" "h"
+    sub "\u04B9" "c"
+    sub "\u04B9\u04CF" "с̇"
+    sub "\u0447" "ç"
+    sub "\u0447\u04CF" "cç̇"
+    sub "\u0448" "ş"
+    sub "\u0449" "şç"
+    sub "\u044A" "’"
+    sub "\u044B" "y"
+    sub "\u044C" ""
+    sub "\u044D" "e"
+    sub "\u044E" "yu"
+    sub "\u044E" "yü"
+    sub "\u044F" "ya"
+    sub "\u044F" "yä"
+    sub "\u04CF" "j"
+  }
+  compose
+}
+
+}

data/maps/bgnpcgn-deu-Latn-Latn-2000.isc

@@ -0,0 +1,68 @@
+system "BGN-PCGN:deu-Latn:Latn:2000" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2000
+  language iso-639-2:deu
+  source_script Latn
+  destination_script Latn
+  name Roman-Script Spelling Convention of German (2000 Agreement)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693794/ROMAN-SCRIPT_SPELLING_CONVENTIONS.pdf
+  creation_date 2000
+
+  notes {
+    note "      The special letter β, known as eszett, [Unicode: 03B2] is a standard letter of the German alphabet and occurs\n      only in word-medial and word-final positions. It is a lowercase letter only, and when a word and/or a name is\n      written entirely in uppercase letters, it is always rendered as SS. As a result of the orthographic reform of\n      German, implemented in August 1998, the β is now rendered ss if it follows a short vowel, but it is still used\n      if it follows a long vowel or a diphthong. In those instances where β cannot be reproduced, the digraph ss\n      may be substituted for it. For alphabetization and sorting purposes, β should be treated as ss."
+    note "      In those instances when the vowel letters ä [Unicode: 00E4], ö [Unicode: 00F6], and ü [Unicode: 00FC]\n      cannot be reproduced, the alternate spellings ae, oe, and ue may be substituted."
+  }
+}
+
+tests {
+   "Dein weiβes Fleisch erregt mich so" ->  "Dein weisses Fleisch erregt mich so"
+   "GROβSTÄDTE" ->  "GROSSSTAEDTE"
+   "Göttingen" ->  "Goettingen"
+   "Gütersloh" ->  "Guetersloh"
+   "Mährisch-Ostrau" ->  "Maehrisch-Ostrau"
+}
+
+dependency "posix"
+
+stage main {
+
+  # RULES
+  sub {
+    from "β" + capture(upper)
+    to "SS" + ref(1)
+    before any(upper)
+  }
+  sub {
+    from "Ä" + capture(upper)
+    to "AE" + ref(1)
+    before any(upper)
+  }
+  sub {
+    from "Ö" + capture(upper)
+    to "OE" + ref(1)
+    before any(upper)
+  }
+  sub {
+    from "Ü" + capture(upper)
+    to "UE" + ref(1)
+    before any(upper)
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "Ä" "Ae"
+    sub "Ö" "Oe"
+    sub "Ü" "Ue"
+
+    sub "ä" "ae"
+    sub "ö" "oe"
+    sub "ü" "ue"
+
+    sub "β" "ss"
+  }
+
+}
+
+}

data/maps/bgnpcgn-div-Thaa-Latn-1972.isc

@@ -0,0 +1,110 @@
+system "BGN-PCGN:div-Thaa:Latn:1972" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1972
+  language iso-639-2:div
+  source_script Thaa
+  destination_script Latn
+  name Romanization of Maldivian (1972)
+  url https://libraries.ucsd.edu/bib/fed/USBGN_romanization.pdf
+  creation_date 1972
+  description ROMANIZATION SYSTEM FOR MALDIVIAN BGN/PCGN 1972 System
+  notes {
+    note "Maldivian writing is read from right to left."
+    note "In the vowel and Diacritical Mark columns x represents any Maldivian consonant character. A Roman vowel letter follows the Romanized Maldivian consonant"
+    note "Alifu(އ) is romanized [’], except when brearing a vowel ,marker, in which case it is not represented in Romanization."
+    note "Nūnu(ނ) appearing immediately before bā, dālu, d̦aviyani, or gāfu, and not braring a vowel marker or sukunu, is romanised [ň];otherwise [n]."
+    note "Where sīnu is followed by hā, or nūnu by yā, a raised dot or slash may be employed in order to differentiate these form shaviyani and nyaviyani respectively"
+  }
+}
+
+tests {
+   "އިރުގައި" ->  "’iruga’i"
+   "ޒިޔާރަތްފުށި" ->  "ziyāratfushi"
+   "ރައްކާތެރިކުރުމާއި" ->  "ra’kāterikurumā’i"
+   "ޝަހީދުންގެ ދުވަސް" ->  "shahīdunge duvas"
+   "ކިހިނެހް" ->  "kihineh"
+   "ކޮން ނަމެއް ކިޔަނީ" ->  "kon name’ kiyanī"
+   "ބައްއަޖޖެވުރި ހެނދުނެހް" ->  "ba’’ajjevuri heňduneh"
+   "މެނދުރެހް" ->  "meňdureh"
+   "ހަވީރެހް" ->  "havīreh"
+   "ސހ" ->  "s·h"
+   "ނޔ" ->  "n·y"
+}
+
+stage main {
+
+  # RULES
+  # rule 3
+  sub {
+    from "\u0787"
+    to "’"
+    not_after "=" + any("\u07a6\u07a7\u07a8\u07a9\u07aa\u07ab\u07ac\u07ad\u07ae\u07af\u07B0")
+  }
+  # rule 4
+  sub {
+    from "\u0782"
+    to "ň"
+    after any("\u0784\u078b\u0791\u078e")
+  }
+
+  # rule 5
+  sub {
+    from "\u0790"
+    to "s·"
+    after any("\u0780")
+  }
+  sub {
+    from "\u0782"
+    to "n·"
+    after any("\u0794")
+  }
+
+
+  # CHARACTERS
+  parallel {
+    # Vowels
+    sub "ަ" "a"
+    sub "ާ" "ā"
+    sub "ެ" "e"
+    sub "ޭ" "ē"
+    sub "ި" "i"
+    sub "ީ" "ī"
+    sub "ު" "u"
+    sub "ޫ" "ū"
+    sub "ޮ" "o"
+    sub "ޯ" "ō"
+    sub "ް" ""
+
+    sub "ހ" "h"
+    sub "ށ" "sh"
+    sub "ނ" "n"
+    sub "ރ" "r"
+    sub "ބ" "b"
+    sub "ޅ" "l̦"
+    sub "ކ" "k"
+    sub "އ" ""
+    sub "ވ" "v"
+    sub "މ" "m"
+    sub "ފ" "f"
+    sub "ދ" "d"
+    sub "ތ" "t"
+    sub "ލ" "l"
+    sub "ގ" "g"
+    sub "ޏ" "ny"
+    sub "ސ" "s"
+    sub "ޝ" "sh"
+    sub "ޑ" "d̦"
+    sub "ޒ" "z"
+    sub "ޓ" "ț"
+    sub "ޔ" "y"
+    sub "ޕ" "p"
+    sub "ޖ" "j"
+    sub "ޗ" "ch"
+  }
+
+  compose
+}
+
+}

data/maps/bgnpcgn-div-Thaa-Latn-1988.isc

@@ -0,0 +1,70 @@
+system "BGN-PCGN:div-Thaa:Latn:1988" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1988
+  language iso-639-2:div
+  source_script Thaa
+  destination_script Latn
+  name Romanization of Maldivian (1988 Agreement, with 2009 modifications)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816778/ROMANIZATION_OF_MALDIVIAN.pdf
+  creation_date 1988
+  confirmation_date 2019
+  description {    This romanization system supersedes the one that was approved by BGN and PCGN in 1972. An
+    official system was submitted to PCGN by the Maldivian government in 1987 and approved by BGN and
+    PCGN in 1988. The system presented here reflects the 1988 Agreement with minor modifications introduced by the government of the Maldives in 2009
+  }
+
+  notes {
+    note "Maldivian is read from right to left."
+    note "The symbol ◌ appearing in the Vowel Characters table represents any Maldivian consonant character."
+    note "The character އ is not romanized. If it bears a vowel character, that vowel character alone is romanized (e.g. އެނބޫދޫ En’boodhoo)."
+    note "      When characters ށ and އ appear in combination with a supercircle (the ‘sukun’, which usually marks\n      the absence of a vowel, see the Diacritical Mark table): ށ ; އ , these characters are not romanized\n      but the following consonant is doubled (e.g. ކަޅުހުރާ Kalhehuttaa), unless the following consonant is a digraph in the\n      romanized form, in which case they are romanized h (e.g. ކެރެށްދޫ Kerehdhoo). ށ and އ appearing at the end of a word are romanized h (e.g. ވޭވައް Veyvah)."
+    note "Noonu (ނ) is romanized n’ when appearing without any vowel or auxiliary sign (e.g. ކަނޑުފުށި Kan’dufushi)"
+    note "Thaa (ތ) is romanized iy when appearing in combination with a supercircle (ތ) ,( e.g. ޒިޔާރަތްފުށި  Ziyaaraiyfushi)."
+    note "The Roman-script columns show only lowercase forms but, when applying the table, uppercase and\n lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+   "އިރުގައި" ->  "irugai"
+   "ޒިޔާރަތްފުށި" ->  "ziyaaraiyfushi"
+   "ރައްކާތެރިކުރުމާއި" ->  "rakkaatherikurumaai"
+   "ޝަހީދުންގެ ދުވަސް" ->  "sh’aheedhun’ge dhuvas"
+   "މަރުޙަބާ" ->  "maruh’abaa"
+   "ކިހިނެހް" ->  "kihin’eh"
+   "ކޮން ނަމެއް ކިޔަނީ" ->  "kon’ n’ameh kiyan’ee"
+   "ބައްއަޖޖެވުރި ހެނދުނެހް" ->  "baajjevuri hen’dhun’eh"
+   "މެނދުރެހް" ->  "men’dhureh"
+   "ހަވީރެހް" ->  "haveereh"
+}
+
+dependency "mv-div-Thaa-Latn-1987" as thaalatn
+
+stage main {
+
+  run  map.thaalatn.stage.main
+
+  # CHARACTERS
+  parallel {
+    #Consonants with diacritical marks (used mainly in words of Arabic origin, corresponding
+    # Arabic characters and their romanizations are shown in parentheses)
+    sub "ޘ" "th’"
+    sub "ޙ" "h’"
+    sub "ޚ" "kh"
+    sub "ޛ" "dh’"
+    sub "ޜ" "x"
+    sub "ޝ" "sh’"
+    sub "ޞ" "s’"
+    sub "ޟ" "l’"
+    sub "ޠ" "t’"
+    sub "ޡ" "z’"
+    sub "ޢ" "’"
+    sub "ޣ" "gh"
+    sub "ޤ" "q"
+    sub "ޥ" "w"
+  }
+
+}
+
+}