From e5e02c52bf91229c447fd7b92bddd2a253977a34 Mon Sep 17 00:00:00 2001 From: Ronald Tse Date: Thu, 7 Oct 2021 17:53:25 +0800 Subject: [PATCH] Add BGNPCGN Dzongkha system 2010 --- maps/bgnpcgn-dzo-Tibt-Latn-2010.imp | 204 ++++++++++++++++++++++++++++ 1 file changed, 204 insertions(+) create mode 100644 maps/bgnpcgn-dzo-Tibt-Latn-2010.imp diff --git a/maps/bgnpcgn-dzo-Tibt-Latn-2010.imp b/maps/bgnpcgn-dzo-Tibt-Latn-2010.imp new file mode 100644 index 0000000..2ef5b6a --- /dev/null +++ b/maps/bgnpcgn-dzo-Tibt-Latn-2010.imp @@ -0,0 +1,204 @@ +metadata { + authority_id: bgnpcgn + id: 2010 + language: iso-639-2:dzo + source_script: Tibt + destination_script: Latn + name: Romanization of Dzongkha (2010 Agreement) + url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693691/ROMANIZATION_OF_DZONGKHA.pdf + creation_date: 2010 + confirmation date: 2017-10 + description: | + + This romanization system for Dzongkha was developed bythe Dzongkha + Development Commission. Bhutan's Ministryof Home Affairs approved this + system in 1997 and mandated that the Bhutanese government use + standardized spellings of geographical names and official guidelines + for romanization. The tabulation shown below is derived from the + version available on the UNGEGN Working Group on Romanization Systems + website. A number of fonts to display Dzongkha are available. The + Bhutanese government provides several Unicode compliant fonts. + + notes: + + - "Dzongkha words are divided into syllables by a special symbol called + tsheg (་) as in the word མ་ thim-phu: Thimphu. Geographical names + greater than three syllables are divided after the second syllable: + e.g. བ་ཤིས་ང་ཙེ (four syllables) tra-shi-yang-tse: Trashi Yangtse." + + - "A syllable may be composed of several elements, including + prefixed, superscript, subscript and suffixed consonant + characters often stacked upon one another, e.g.  s + (superscript) upon k upon ya (subscript) generating skya." + + - "Prefixed consonants are not romanized, e.g. གང ་ནག Dungna + [ག (prefix)  (root with vowel marking) ང (suffix) ་ + (syllable break) ན (root) ག (suffix)] and མགར་ས Gasa [མ + (prefix) ག (root) ར (suffix) ་ (syllable break) ས (root)]." + + - Superscript consonants are not romanized with the + exception of  lha, e.g. བསགས་ང Sakteng [བ (prefix) ས (root) + ག (suffix) ས (secondary suffix) ་ (syllable break)  (root + with superscript and vowel marking) ང(suffix)]; ང་་ས + Tangsibji [ (root with superscript) ང (suffix) ་ (syllable + break)  (root with vowel marking) ་ (syllable break)  + (root with subscript, superscript, and vowel marking) ས + (suffix)], but ན་་ Lhuentse [ (root with subscript and + vowel marking) ན (suffix) ་ (syllable beak)  (root with + vowel marking)]. + + - Suffixed consonants are romanized or not romanized based + on local pronunciation, e.g. ང ་ཁག Drungkhag [ (root with + subscript and vowel marking) ང (suffix) ་ (syllable break) ཁ + (root) ག (suffix)], དབང ་ག Wangchhuk [ད(prefix) བ(root) + ང(suffix) ་ (syllable break)  (root with subscript and + vowel marking) ག (suffix)], ག Ta [ (root with + superscript) ག (suffix)]. + + - Secondary suffixed consonants are not romanized; however, + there are exceptions, e.g. བར་མཚམས Bartsham [བ (root) ར + (suffix) ་ (syllable break) མ (prefix) ཚ (root) མ (suffix) ས + (secondary suffix)], ངས་ Dangchhu [ (root with + subscript) ང (suffix) ས (secondary suffix) ་ (syllable + break)  (root with vowel marking)]. གཞལམ་ང Zhemgang [ག + (prefix) ཞ (root) ལ (suffix) མ (secondary suffix) ་(syllable + break)  (root with superscript) ང (suffix)] is an + exception in which the suffix is not romanized but the + secondary suffix is romanized. + + # Special Notes: + - Pronunciation of Dzongkha names may vary according to + local usage and there are several exceptions to the present + romanization guidelines. + + - "Additional characters that are found mainly in words of Indic + provenance are romanized as follows: ཊ tra, ཋ thra, ཌ dra, ཎ na, ཥ kha, + ཀྵ chha." + +} + +tests { + test "ཐྀམ་ཕུ", "Thimphu" + test "བཀྲ་ཤིས་གྱང་ཙེ", "Trashi Yangtse" + test "སྟང་སི་སྦྱིས", "Tangsibji" + +stage { + + # CHARACTERS + parallel { +map: + characters: + sub "\u0F40", "ka" # ཀ + sub "\u0F41", "kha" # ཁ + sub "\u0F42", "ga" # ག + sub "\u0F44", "nga" # ང + sub "\u0F45", "cha" # ཅ + sub "\u0F46", "chha" # ཆ + sub "\u0F47", "ja" # ཇ + sub "\u0F49", "mya" # ཉ + sub "\u0F4F", "ta" # ཏ + sub "\u0F50", "tha" # ཐ + sub "\u0F51", "da" # ད + sub "\u0F53", "na" # ན + sub "\u0F54", "pa" # པ + sub "\u0F55", "pha" # ཕ + sub "\u0F56", any([ + - 'ba' # བ + - 'wa' # བ + sub "\u0F58", "ma" # མ + sub "\u0F59", "tsa" # ཙ + sub "\u0F5A", "tsha" # ཚ + sub "\u0F5B", "dza" # ཛ + sub "\u0F5D", "wa" # ཝ + sub "\u0F5E", "zha" # ཞ + sub "\u0F5F", "za" # ཟ + sub "\u0F60", "z" # འ + sub "\u0F61", "ya" # ཡ + sub "\u0F62", "ra" # ར + sub "\u0F63", "la" # ལ + sub "\u0F64", "sha" # ཤ + sub "\u0F66", "sa" # ས + sub "\u0F67", "ha" # ཧ + sub "\u0F68", "a" # ཨ + + # a) The character '\u0F56' is romanized as either ba + # or wa depending on dialect. See special note number 1. + + # b) The subscript variant of the character '\u0F5D' + # (wa): '\u0FAD' is not romanized: '\u0F41\u0FAD' ka, + # '\u0F51\u0FAD' da, '\u0F5A\u0FAD' tsha. + + # c) The subscript variant of the character '\u0F61' is + # '\u0FB1' (ya), e.g. '\u0F40\u0FB1'. See syllable + # initial consonant combination table for romanized forms. + + # d) The superscript variant of character '\u0F62' (ra) + # is not romanized:  ka,  da,  dza. The subscript + # variant of this character is ◌ྲ: see syllable initial + # consonant combination table for romanized forms. + + # Vowels (where ཨ stands for any consonant character): + + # Romanized e or ay if followed by a suffix ད་ ན་ འ་ ས་ + sub "\u0F68", "a" # ཨ (see note a) + sub "\u0f68\u0f72", "i" # ཨི + + # Romanized ue or u if followed by a suffix ད་ ན་ འ་ ས་ + sub "\u0f40\u0f74", "u" # ཀུ (see note b) + sub "\u0F68\u0F7A", "e" # ཨེ + + # Romanized oe or o if followed by a suffix ད་ ན་ འ་ ས་ + sub "\u0F68\u0F7C", "o" # ཨོ (see note c) + + # a) Romanized e or ay if followed by a suffix ད་ ན་ འ་ ས་ + # b) Romanized ue or u if followed by a suffix ད་ ན་ འ་ ས་ + # c) Romanized oe or o if followed by a suffix ད་ ན་ འ་ ས་ + + + # Syllable-initial Consonant Combinations (This list is + # not complete. Only those consonant clusters with non-standard + # romanizations are given. Also see “General guidelines before transliterating”.): + + sub "\u0F40\u0FB1", any(["cha", "ka"]) # ཀྱ and note A + sub "\u0F41\u0FB1", any(["chha", "kha"]) # (see note A) + sub "\u0F42\u0FB1", any(["ja", "gya"]) # (see note A) + sub "\u0F54\u0FB1", any(["cha", "pcha"]) + sub "\u0F54\u0FB1", any(["chha", "pchha"]) + sub "\u0F56\u0FB1", any(["ja", "bja"]) + sub "\u0f51\u0F56\u0FB1", "ya" + sub "\u0f58\u0FB1", "nya" + sub "\u0F40\u0FB2", "tra" # ཀྲ + sub "\u0F41\u0FB2", "thra" # ཁྲ + sub "\u0F42\u0FB2", "dra" # གྲ + # sub "", "tra" # 12. (unicode not found) + sub "\u0F50\u0FB2", "thra" # ཐྲ + sub "\u0f51\u0FB2", "dra" # དྲ + sub "\u0F54\u0FB2", "tra" # པྲ + sub "\u0F55\u0FB2", "thra" # ཕྲ + sub "\u0F56\u0FB2", "dra" # བྲ + sub "\u0F64\u0FB2", "shra" # ཤྲ + sub "\u0F66\u0FB2", "sa" # སྲ + # sub "", "hra" # 20. (unicode not found) + sub "\u0F51\u0F56", "wa" # དབ (see note B) + sub "\u0F5F\u0FA8", "da" # ཟྨ + sub "\u0F63\u0FB7", "lha" # ལྷ + + # A) Palatal variants ch, chh, j are generally used before a, o, and u. + # B) Not romanized if followed by any other vowel than a. + + # Syllable Endings (suffixes): + sub "\u0F42", any(["g", "k"]) # ག. or not romanized + + sub "\u0F44", "ng" # or not romanized + sub "\u0F51", "" # Not romanized + sub "\u0F53", "n" # or not romanized + + sub "\u0F56", any(["b", "p"]) # བ + + sub "\u0F58", "m" # མ + sub "\u0F60", "" # not romanized + sub "\u0F62", "r" # or not romanized + sub "\u0F63", "I" # or not romanized + sub "\u0F66", "" # not romanized + } +} \ No newline at end of file