interscript-maps 2.4.2 → 2.5.0

data/maps/bgnpcgn-mon-Cyrl-Latn-1964.isc

@@ -0,0 +1,186 @@
+system "BGN-PCGN:mon-Cyrl:Latn:1964" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1964
+  language iso-639-2:mon
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Mongolian (1964)
+  url https://github.com/interscript/interscript/files/5180767/BGN_Romanization_Guide_1964_mongolian_1964.pdf
+  creation_date 1964
+  confirmation_date 1964
+  description {    This system was originated by the PCGN in 1957 and adopted as a
+    BGN/PCGN System in 1964. It is intended for use in the romanization of
+    geographic names in the "Mongolian People's Republic" but not to romanize
+    Mongolian names in adjacent parts of China and the U.S.S.R.
+  }
+
+  notes {
+    note "    - b occurs initially and after л, м, and б.\n    - v occurs medially in Mongolian words and initially in foreign words.\n    - y occurs only as the second element of diphthongs.\n    - k, p, f, and shch occurs foreign words only.\n    - \"\\u2019\" occurs only in Russion words.\n    - ï occurs only in suffixes to words containing back vowels (a, o, and u).\n    - In monosyllables yu or yü depending on pronunciation; in polysyllables yu when followed by a, o, or u, but yü when followed by i, e, ö, or ü."
+  }
+}
+
+tests {
+   "Эрдэнэт Сум" ->  "Erdenet Sum"
+   "Эрдэнэт" ->  "Erdenet"
+   "Эрдэнэ" ->  "Erdene"
+   "Шивээговь Сум" ->  "Shiveegovĭ Sum"
+   "Шивээговь" ->  "Shiveegovĭ"
+   "Шарынгол Сум" ->  "Sharïngol Sum"
+   "Шарынгол" ->  "Sharïngol"
+   "Цагааннуур" ->  "Tsagaannuur"
+   "Хонгор Сум" ->  "Hongor Sum"
+   "Хонгор" ->  "Hongor"
+   "Хайлаастай" ->  "Haylaastay"
+   "Түнэл Сум" ->  "Tünel Sum"
+   "Түнэл" ->  "Tünel"
+   "Сүхбаатар" ->  "Sühbaatar"
+   "Сүмбэр Сум" ->  "Sümber Sum"
+   "Сүмбэр" ->  "Sümber"
+   "Сайншанд Сум" ->  "Saynshand Sum"
+   "Сайншанд" ->  "Saynshand"
+   "Орхон Сум" ->  "Orhon Sum"
+   "Орхон" ->  "Orhon"
+   "Нарст" ->  "Narst"
+   "Мөрөн Сум" ->  "Mörön Sum"
+   "Мөрөн" ->  "Mörön"
+   "Зүүнхөвөө" ->  "Dzüünhövöö"
+   "Жаргалант Сум" ->  "Jargalant Sum"
+   "Жаргалант" ->  "Jargalant"
+   "Дархан Сум" ->  "Darhan Sum"
+   "Даланзадгад Сум" ->  "Dalandzadgad Sum"
+   "Даланзадгад" ->  "Dalandzadgad"
+   "Давст Сум" ->  "Davst Sum"
+   "Давст" ->  "Davst"
+   "Говьсүмбэр Сум" ->  "Govĭsümber Sum"
+   "Говь" ->  "Govĭ"
+   "Буга" ->  "Buga"
+   "Бор-Өндөр Сум" ->  "Bor-Öndör Sum"
+   "Бор-Өндөр" ->  "Bor-Öndör"
+   "Баянхонгор" ->  "Bayanhongor"
+   "Баянтал" ->  "Bayantal"
+   "Баяндэлгэр Сум" ->  "Bayandelger Sum"
+   "Баяндэлгэр" ->  "Bayandelger"
+   "Баян-Өндөр Сум" ->  "Bayan-Öndör Sum"
+   "Баруун-Урт Сум" ->  "Baruun-Urt Sum"
+   "Баруун-Урт" ->  "Baruun-Urt"
+   "Архуст" ->  "Arhust"
+   "Арвайхээр Сум" ->  "Arvayheer Sum"
+   "Арвайхээр" ->  "Arvayheer"
+   "Есөнбулаг Сум" ->  "Yösönbulag Sum"
+   "Ерөө Сум" ->  "Yöröö Sum"
+   "Есөнзүйл Сум" ->  "Yösöndzüyl Sum"
+   "Ноён Сум" ->  "Noyon Sum"
+   "Родник Балянгийн-Булак" ->  "Rodnik Balyangiyn-Bulak"
+   "Замын-Үүд Сум" ->  "Dzamïn-Üüd Sum"
+   "Адаацаг Сум" ->  "Adaatsag Sum"
+   "Чандмань Сум" ->  "Chandmanĭ Sum"
+   "Хяргас Сум" ->  "Hyargas Sum"
+
+  # Note: UN card expects "uls" to start with an uppercase letter, but that would break other tests
+   "Монгол улс" ->  "Mongol uls"
+   "Улаанбаатар" ->  "Ulaanbaatar"
+}
+
+stage main {
+
+  # RULES
+  sub {
+    from "\u042e"
+    to "Yu"
+    after any("АаОоУу")
+  }
+  sub {
+    from "\u044e"
+    to "yu"
+    after any("АаОоУу")
+  }
+  sub {
+    from "\u042e"
+    to "Yü"
+    after any("ИиЭэӨөҮү")
+  }
+  sub {
+    from "\u044e"
+    to "yü"
+    after any("ИиЭэӨөҮү")
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "Yö"
+    sub "Ё" "Yo"
+    sub "Ж" "J"
+    sub "З" "Dz"
+    sub "И" "I"
+    sub "Й" "Y"
+    sub "К" "K"
+    sub "Л" "L"
+    sub "М" "M"
+    sub "Н" "N"
+    sub "О" "O"
+    sub "Ө" "Ö"
+    sub "П" "P"
+    sub "Р" "R"
+    sub "С" "S"
+    sub "Т" "T"
+    sub "У" "U"
+    sub "Ү" "Ü"
+    sub "Ф" "F"
+    sub "Х" "H"
+    sub "Ц" "Ts"
+    sub "Ч" "Ch"
+    sub "Ш" "Sh"
+    sub "Щ" "Shch"
+    sub "Ъ" "’"
+    sub "Ы" "Ï"
+    sub "Ь" "Ĭ"
+    sub "Э" "E"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "yö"
+    sub "ё" "yo"
+    sub "ж" "j"
+    sub "з" "dz"
+    sub "и" "i"
+    sub "й" "y"
+    sub "к" "k"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "ө" "ö"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ү" "ü"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ц" "ts"
+    sub "ч" "ch"
+    sub "ш" "sh"
+    sub "щ" "shch"
+    sub "ъ" "’"
+    sub "ы" "ï"
+    sub "ь" "ĭ"
+    sub "э" "e"
+    sub "ю" "yu"
+    sub "я" "ya"
+  }
+
+}
+}

data/maps/bgnpcgn-nep-Deva-Latn-2011.isc

@@ -0,0 +1,203 @@
+system "BGN-PCGN:nep-Deva:Latn:2011" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2011
+  language iso-639-2:nep
+  source_script Deva
+  destination_script Latn
+  name Romanization for Nepali (2011 Agreement)
+  url https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20NEPALI.pdf
+  creation_date 2011
+  confirmation_date 2017
+  description {    The BGN and the PCGN have adopted the Nepal Survey Department (NSD) system for the
+    romanization of Nepali names.  This system, below, should be applied to Nepali names for which Roman‐
+    script spellings in materials produced by the government of Nepal are not available.
+  }
+
+  notes {
+
+    note "Only the isolated forms of the characters are given in the consonant table.  See any grammar of Nepali\n (or other language using the Devanagari alphabet) for variant forms used in conjunct characters."
+    note "These two consonant characters appear sometimes to represent ṛ (cerebral r), e.g., पहाड  →  pahāṛ\n instead of pahāḍ.  At one time they were written with dots below, i.e., as ड़ and ढ़, though this is no\n longer normal practice in Nepali.    The romanizations ṛ and ṛh, respectively, are optional for\n documentary purposes if such dots appear in Nepali writing."
+    note "व , can be romanized as either v or w.    This character is primarily\n romanized as v in consonant initial, medial, and final position; however, initial, medial, and final w\n romanizations can occur. The w romanization is a special case which is believed to be dependent on\n dialect, pronunciation, or stress."
+    note "      An inventory of letter‐diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:\n        Ṅ(U+1E44)  ṅ (U+1E45)\n        Ñ (U+00D1) ñ (U+00F1)\n        Ṭ (1E6C)   ṭ (1E6D)\n        Ḍ (1E0C)   ḍ (1E0D)\n        Ṇ (1E46)   ṇ (1E47)\n        Ṣ (1E62)   ṣ (1E63)\n        Ā (U+0100) ā (U+0101)\n        Ī (U+012A) ī (U+012B)\n        Ū (U+016A) ū (U+016B)\n        Ṛ (1E5A)   ṛ (1E5B)"
+
+    note "The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase\n Roman letters as appropriate should be used."
+
+    note "      ं (anusvara) is rendered by\n      ṅ before क, ख, ग, and घ\n      ñ before च, छ, ज, and झ\n      ṇ before ट, ठ, ड, and ढ\n      n before त, थ, द, and ध\n      ṁ before य, र, ल, व, श, ष, स and ह"
+  }
+}
+
+tests {
+   "लेखन" ->  "lekhn"
+   "मुद्रा" ->  "mudarā"
+   "प्रशंसा" ->  "parshṃsā" # note 5 rule checking
+   "अंक" ->  "aṅk" # note 5 rule checking
+   "नेकपाले स्थगित स्थायी कमिटीको बैठक भदौ गते बोलाउने भएको" ->  "nekpāle sathgit sathāyī kmiṭīko baiṭhk bhdau gte bolāune bheko"
+   "न घर रह्यो, न परिवार" ->  "n ghr rhayo, n privār"
+   "ढोरपाटनमा भुजीखोला बाढीपहिरोले अभिभावक गुमाएका बालबालिकाको बिचल्ली" ->  "ḍhorpāṭnmā bhujīkholā bāḍhīphirole abhibhāvk gumāekā bālbālikāko bichlalī"
+   "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो" ->  "susamitākā kākā hembhādur r kākīlāī pni phirole bgāyo"
+   "संविधान जारी भएसँगै सार्वजनिक प्रशासनमा नयाँ उत्साह आउने अपेक्षा थियो" ->  "sṃvidhān jārī bhes~gai sāravjnik parshāsnmā nyā~ utasāh āune apekṣā thiyo"
+   "देशमा कोरोना संक्रमित र मृतकको संख्या हरेक दिन बढ्दो छ" ->  "deshmā koronā sṅkarmit r mṛitkko sṅkhayā hrek din bḍhado chh"
+   "गाउँपालिकाका अध्यक्ष टिका गुरुङका अनुसार विष्णुदासलाई राजुले सुत्नका लागि बेलुका साथी लगेका थिए" ->  "gāu~pālikākā adhaykṣ ṭikā guruṅkā anusār viṣaṇudāslāī rājule sutankā lāgi belukā sāthī lgekā thie"
+   "यो आयोजना गाउँपालिकाको केन्द्र तेल्लोकमा पर्छ" ->  "yo āyojnā gāu~pālikāko kenadar telalokmā prachh"
+   "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो" ->  "susamitākā kākā hembhādur r kākīlāī pni phirole bgāyo"
+   "चैत पहिलो साता घर आएका उनी लकडाउन भएपछि यतै रोकिए" ->  "chait philo sātā ghr āekā unī lkḍāun bhepchhi ytai rokie"
+   "काम गर्न जानेको हकमा रोजगारदाता कम्पनीको पत्रसँगै वडा र जिल्ला प्रशासनको सिफारिस अनिवार्य गरिएको छ" ->  "kām gran jāneko hkmā rojgārdātā kmapnīko ptrs~gai vḍā r jilalā parshāsnko siphāris anivāray grieko chh"
+   "दुःख" ->  "duḥkh"
+   "निकुञ्जको स्थानीय पोस्टका कर्मचारी पनि त्यहीँ थिए" ->  "nikuñajko sathānīy posaṭkā kramchārī pni tayhī~ thie"
+   "युद्धकालको मनोविज्ञान" ->  "yudadhkālko mnovijñān"
+   "जर्मन वायुसेवाको आक्रमणमा दुई लाख पचास हजार मानिसको ज्यान जानसक्ने र करिब ३० देखि ४० लाख मान्छे विस्थापित हुने अनुमान बेलायत सरकारको थियो" ->  "jramn vāyusevāko ākarmṇmā duī lākh pchās hjār mānisko jayān jānskane r krib 30 dekhi 40 lākh mānachhe visathāpit hune anumān belāyt srkārko thiyo"
+   "युद्ध" ->  "yudadh"
+   "कोरोनासँग जम्काभेट" ->  "koronās~g jmakābheṭ"
+   "संक्रमित" ->  "sṅkarmit"
+   "स्वयम्" ->  "savyma"
+   "संख्या" ->  "sṅkhayā"
+   "गौरीटारस्थित रंगशाला" ->  "gaurīṭārsathit rṅgshālā"
+}
+
+stage main {
+
+  # RULES
+  # note[5]
+  sub {
+    from "\u0902"
+    to "ṅ"
+    after any("कखगघ")
+  }
+  sub {
+    from "\u0902"
+    to "ñ"
+    after any("चछजझ")
+  }
+  sub {
+    from "\u0902"
+    to "ṇ"
+    after any("टठडढ")
+  }
+  sub {
+    from "\u0902"
+    to "n"
+    after any("तथदध")
+  }
+
+
+  # CHARACTERS
+  parallel {
+
+    # Vowels and Diphthongs
+
+    sub "अ" "a"
+    sub "आ" "ā"
+    sub "इ" "i"
+    sub "ई" "ī"
+    sub "उ" "u"
+    sub "ऊ" "ū"
+    sub "ऋ" "ṛi"
+    sub "ॠ" "rī"
+    sub "ए" "e"
+    sub "ऐ" "ai"
+    sub "ओ" "o"
+    sub "औ" "au"
+
+    # Medials # Needed for connecting constants
+
+    sub "ा" "ā"
+    sub "ि" "i"
+    sub "ी" "ī"
+    sub "ु" "u"
+    sub "ू" "ū"
+    sub "ृ" "ṛi"
+    sub "ॄ" "rī"
+    sub "े" "e"
+    sub "ै" "ai"
+    sub "ो" "o"
+    sub "ौ" "au"
+
+
+    # Consonants (see Note 1)
+
+    # Gutturals
+    sub "क" "k"
+    sub "ख" "kh"
+    sub "ग" "g"
+    sub "घ" "gh"
+    sub "ङ" "ṅ"
+
+    # Palatals
+    sub "च" "ch"
+    sub "छ" "chh"
+    sub "ज" "j"
+    sub "झ" "jh"
+    sub "ञ" "ñ"
+
+    # Cerebrals
+    sub "ट" "ṭ"
+    sub "ठ" "ṭh"
+    sub "ड" "ḍ"
+    sub "ढ" "ḍh"
+    sub "ण" "ṇ"
+
+    # Dentals
+    sub "त" "t"
+    sub "थ" "th"
+    sub "द" "d"
+    sub "ध" "dh"
+    sub "न" "n"
+
+    # Labials
+    sub "प" "p"
+    sub "फ" "ph"
+    sub "ब" "b"
+    sub "भ" "bh"
+    sub "म" "m"
+
+    # Semivowels
+    sub "य" "y"
+    sub "र" "r"
+    sub "ल" "l"
+    sub "व" "v"
+
+    # Sibilants
+    sub "श" "sh"
+    sub "ष" "ṣ"
+    sub "स" "s"
+    sub "क्ष" "kṣ"
+    sub "त्र" "tr"
+    sub "ज्ञ" "jñ"
+
+    # Aspirate
+    sub "ह" "h"
+
+    # Anusvāra
+    sub "ं" "ṃ"
+
+    # Bisarga
+    sub "ः" "ḥ"
+
+    # Anunāsika
+    sub "ँ" "~"
+
+    sub "ॅ" "r"
+
+    # halanta
+    sub "्" "a"
+
+    # Abagraha
+    sub "ऽ" "’"
+
+    # Numerals / सङ्ख्या
+    sub "०" "0"
+    sub "१" "1"
+    sub "२" "2"
+    sub "३" "3"
+    sub "४" "4"
+    sub "५" "5"
+    sub "६" "6"
+    sub "७" "7"
+    sub "८" "8"
+    sub "९" "9"
+  }
+  compose
+}
+}