interscript-maps 2.0.5

data/maps/un-hin-Deva-Latn-2016.imp

@@ -0,0 +1,356 @@
+metadata {
+  authority_id: ungegn
+  id: 2016
+  language: iso-639-2:hin
+  source_script: Deva
+  destination_script: Latn
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Hindi Romanization, 1972
+  url: https://www.eki.ee/wgrs/rom1_hi.pdf
+  creation_date: 1972
+  confirmation_date: 2016
+  description: |
+    The United Nations recommended system was approved in 1972 (II/11) and amended in 1977
+    (III/12), based on a report prepared by D. N. Sharma. The tables and their corrections were
+    published in volume II of the conference reports.
+
+    There is no evidence of the use of the system either in India or in international cartographic
+    products. It was stated in 1987 that the appropriate resolution had not been implemented in
+    India and the Hunterian system was still in use in large-scale mapping
+
+    Hindi uses the alphasyllabic script Devanāgarī whereby each character represents a syllable
+    rather than one sound. Vowels and diphthongs are marked in two ways: as independent
+    characters (used syllable-initially) and in an abbreviated form, to denote vowels after
+    consonants. The romanization table is unambiguous but the user would have to recognize
+    many ligatures not given in the original table (only three are given). The system is mostly
+    reversible but there may exist some ambiguities in the romanization of vowels (independent
+    vs. abbreviated characters) and consonants
+
+  notes:
+    - |
+      It is recommended that the vowel अ (a) should always be romanized except when it ends a
+      name. If a name ends with a consonant, the consonant should carry a sub-macron. Such
+      cases, however, will be very rare. For example, कानपुर Kānapur (not Kānapura), जगत्
+      Jagat.
+    - |
+      If each letter of a digraph or any two parts of a trigraph has a distinct independent sound
+      then it should be indicated by a hyphen, thus d-h.
+
+    ######################################## Additional Note ############################################################
+    #    It is recommended that the vowel अ (a) should always be romanized except when it ends a                        #
+    #    name. In the scheme we are not yet able to detect a name. Analysing language pattern and the example           #
+    #    we found that actually when a word ends with a consonant it should be transliterated without the vowel in it.  #
+    #    so we are applying this rule as if a word ends with a consonant, in this case we are removing the ending 'a'.  #
+    #####################################################################################################################
+}
+
+tests {
+  test "दिल्ली", "dillī"
+  test "भारत", "bhārat"
+  test "परिपक्क", "paripakk"
+  test "जगत्", "jagat"
+  test "संख्या", "saṁkhyā"
+  test "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर", "gaṁbhīr marījoṁ ke māmale meṁ bhārat dūsare naṁbar par"
+  test "कोरोना अपडेट्स", "koronā apaḍeṭs"
+  test "सीडीसी चीफ का बयान अहम", "sīḍīsī chīph kā bayān aham"
+  test "गूगल प्ले स्टोर पर पेटीएम की वापसी", "gūgal ple sṭor par peṭīem kī vāpasī"
+  test "भारत में गैंबलिंग की इजाजत नहीं", "bhārat meṁ gaiṁbaliṁg kī ijājat nahīṁ"
+  test "कोरोना वैक्सीन मुद्दे पर घिरे राष्ट्रपति; जो बाइडेन बोले- मुझे और देश को वैज्ञानिकों पर भरोसा है, डोनाल्ड ट्रम्प पर नहीं", "koronā vaiksīn mudde par ghire rāṣhṭrapati; jo bāiḍen bole- mujhe aur desh ko vaijñānikoṁ par bharosā hai, ḍonālḍ ṭramp par nahīṁ"
+  test "गूगल की कार्रवाई पर पेटीएम ने कहा था कि ऐप को अस्थायी तौर पर प्ले-स्टोर से हटाया गया है, आपके पैसे सुरक्षित हैं", "gūgal kī kārravāī par peṭīem ne kahā thā ki aip ko asthāyī taur par ple-sṭor se haṭāyā gayā hai, āpake paise surakṣhit haiṁ"
+}
+
+
+aliases {
+  def_alias deva_characters_1, any("\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d")
+}
+
+stage {
+
+  # RULES
+  sub "क" + maybe("="), "k", after: deva_characters_1
+  sub "क", "k", after: boundary
+
+  sub "ख" + maybe("="), "kh", after: deva_characters_1
+  sub "ख", "kh", after: boundary
+
+  sub "ग" + maybe("="), "g", after: deva_characters_1
+  sub "ग", "g", after: boundary
+
+  sub "घ" + maybe("="), "gh", after: deva_characters_1
+  sub "घ", "gh", after: boundary
+
+  sub "ङ" + maybe("="), "ṅ", after: deva_characters_1
+  sub "ङ", "ṅ", after: boundary
+
+  sub "च" + maybe("="), "ch", after: deva_characters_1
+  sub "च", "ch", after: boundary
+
+  sub "छ" + maybe("="), "chh", after: deva_characters_1
+  sub "छ", "chh", after: boundary
+
+  sub "ज" + maybe("="), "j", after: deva_characters_1
+  sub "ज", "j", after: boundary
+
+  sub "झ" + maybe("="), "jh", after: deva_characters_1
+  sub "झ", "jh", after: boundary
+
+  sub "ञ" + maybe("="), "ñ", after: deva_characters_1
+  sub "ञ", "ñ", after: boundary
+
+  sub "ट" + maybe("="), "ṭ", after: deva_characters_1
+  sub "ट", "ṭ", after: boundary
+
+  sub "ठ" + maybe("="), "ṭh", after: deva_characters_1
+  sub "ठ", "ṭh", after: boundary
+
+  sub "ड" + maybe("="), "ḍ", after: deva_characters_1
+  sub "ड", "ḍ", after: boundary
+
+  sub "ढ" + maybe("="), "ḍh", after: deva_characters_1
+  sub "ढ", "ḍh", after: boundary
+
+  sub "ण" + maybe("="), "ṇ", after: deva_characters_1
+  sub "ण", "ṇ", after: boundary
+
+  sub "त" + maybe("="), "t", after: deva_characters_1
+  sub "त", "t", after: boundary
+
+  sub "थ" + maybe("="), "th", after: deva_characters_1
+  sub "थ", "th", after: boundary
+
+  sub "द" + maybe("="), "d", after: deva_characters_1
+  sub "द", "d", after: boundary
+
+  sub "ध" + maybe("="), "dh", after: deva_characters_1
+  sub "ध", "dh", after: boundary
+
+  sub "न" + maybe("="), "n", after: deva_characters_1
+  sub "न", "n", after: boundary
+
+  sub "प" + maybe("="), "p", after: deva_characters_1
+  sub "प", "p", after: boundary
+
+  sub "फ" + maybe("="), "ph", after: deva_characters_1
+  sub "फ", "ph", after: boundary
+
+  sub "ब" + maybe("="), "b", after: deva_characters_1
+  sub "ब", "b", after: boundary
+
+  sub "भ" + maybe("="), "bh", after: deva_characters_1
+  sub "भ", "bh", after: boundary
+
+  sub "म" + maybe("="), "m", after: deva_characters_1
+  sub "म", "m", after: boundary
+
+  sub "य" + maybe("="), "y", after: deva_characters_1
+  sub "य", "y", after: boundary
+
+  sub "र" + maybe("="), "r", after: deva_characters_1
+  sub "र", "r", after: boundary
+
+  sub "ल" + maybe("="), "l", after: deva_characters_1
+  sub "ल", "l", after: boundary
+
+  sub "व" + maybe("="), "v", after: deva_characters_1
+  sub "व", "v", after: boundary
+
+  sub "श" + maybe("="), "sh", after: deva_characters_1
+  sub "श", "sh", after: boundary
+
+  sub "ष" + maybe("="), "ṣh", after: deva_characters_1
+  sub "ष", "ṣh", after: boundary
+
+  sub "स" + maybe("="), "s", after: deva_characters_1
+  sub "स", "s", after: boundary
+
+  sub "क़" + maybe("="), "q", after: deva_characters_1
+  sub "क़", "q", after: boundary
+
+  sub "ख़" + maybe("="), "ḳh", after: deva_characters_1
+  sub "ख़", "ḳh", after: boundary
+
+  sub "ग़" + maybe("="), "g", after: deva_characters_1
+  sub "ग़", "g", after: boundary
+
+  sub "ज़" + maybe("="), "z", after: deva_characters_1
+  sub "ज़", "z", after: boundary
+
+  sub "ड़" + maybe("="), "ṙ", after: deva_characters_1
+  sub "ड़", "ṙ", after: boundary
+
+  sub "ढ़" + maybe("="), "ṙh", after: deva_characters_1
+  sub "ढ़", "ṙh", after: boundary
+
+  sub "फ़" + maybe("="), "f", after: deva_characters_1
+  sub "फ़", "f", after: boundary
+
+  sub "ह" + maybe("="), "h", after: deva_characters_1
+  sub "ह", "h", after: boundary
+
+
+  # CHARACTERS
+  parallel {
+
+    # I. Independent vowel characters
+    sub "अ", "a"
+    sub "आ", "ā"
+    sub "इ", "i"
+    sub "ई", "ī"
+    sub "उ", "u"
+    sub "ऊ", "ū"
+    sub "ऋ", "ṛ"
+    sub "ॠ", "ṝ"
+    sub "ऌ", "l̤"
+    sub "ए", "e"
+    sub "ऐ", "ai"
+    sub "ओ", "o"
+    sub "औ", "au"
+
+    # II. Abbreviated vowel characters
+
+    sub "ा", "ā" # का
+    sub "ॉ", "ā̆ " #  additional mark: कॉ
+    sub "ि", "i" # कि i
+    sub "ी", "ī" # की
+    sub "ु", "u" # कु
+    sub "ू", "ū" # कू
+    sub "ृ", "ṛ" # कृ
+    sub "े", "e" # के
+    sub "ै", "ai" # कै
+    sub "ो", "o" # को
+    sub "ौ", "au" # कौ
+
+
+    # Consonants (see Note 1)
+
+    # Gutturals
+    sub "क", "ka"
+    sub "ख", "kha"
+    sub "ग", "ga"
+    sub "घ", "gha"
+    sub "ङ", "ṅa"
+
+    # Palatals
+    sub "च", "cha"
+    sub "छ", "chha"
+    sub "ज", "ja"
+    sub "झ", "jha"
+    sub "ञ", "ña"
+
+    # Cerebrals
+    sub "ट", "ṭa"
+    sub "ठ", "ṭha"
+    sub "ड", "ḍa"
+    sub "ढ", "ḍha"
+    sub "ण", "ṇa"
+
+    # Dentals
+    sub "त", "ta"
+    sub "थ", "tha"
+    sub "द", "da"
+    sub "ध", "dha"
+    sub "न", "na"
+
+    # Labials
+    sub "प", "pa"
+    sub "फ", "pha"
+    sub "ब", "ba"
+    sub "भ", "bha"
+    sub "म", "ma"
+
+    # Semivowels
+    sub "य", "ya"
+    sub "र", "ra"
+    sub "ल", "la"
+    sub "व", "va"
+
+    # Sibilants
+    sub "श", "sha"
+    sub "ष", "ṣha"
+    sub "स", "sa"
+
+    # Dotted variants
+    sub "क़", "qa"
+    sub "ख़", "ḳha"
+    sub "ग़", "ġa"
+    sub "ज़", "za"
+    sub "ड़", "ṙa"
+    sub "ढ़", "ṙha"
+    sub "फ़", "fa"
+
+
+    # Aspirate
+    sub "ह", "ha"
+
+    # Anusvāra
+    sub "ं", "ṁ"
+
+    # Anunāsika
+    sub "ँ", "m̐"
+
+    # halanta
+    sub "्", ""
+
+    # bisharga
+    sub "ः", "ḥ"
+
+    #V. Ligatures(To cover all Ligatures at unicode)
+    #  Implemnting Pronunciation without a vowel: क् k.
+
+    # Gutturals
+    sub "क्", "k"
+    sub "ख्", "kh"
+    sub "ग्", "g"
+    sub "घ्", "gh"
+    sub "ङ्", "ṅ"
+
+    # Palatals
+    sub "च्", "ch"
+    sub "छ्", "chh"
+    sub "ज्", "j"
+    sub "झ्", "jh"
+    sub "ञ्", "ñ"
+
+    # Cerebrals
+    sub "ट्", "ṭ"
+    sub "ठ्", "ṭh"
+    sub "ड्", "ḍ"
+    sub "ढ्", "ḍh"
+    sub "ण्", "ṇ"
+
+    # Dentals
+    sub "त्", "t"
+    sub "थ्", "th"
+    sub "द्", "d"
+    sub "ध्", "dh"
+    sub "न्", "n"
+
+    # Labials
+    sub "प्", "p"
+    sub "फ्", "ph"
+    sub "ब्", "b"
+    sub "भ्", "bh"
+    sub "म्", "m"
+
+    # Semivowels
+    sub "य्", "y"
+    sub "र्", "r"
+    sub "ल्", "l"
+    sub "व्", "v"
+
+    # Sibilants
+    sub "श्", "sh"
+    sub "ष्", "ṣh"
+    sub "स्", "s"
+
+    # Dotted variants
+    sub "क़्", "q"
+    sub "ख़्", "ḳh"
+    sub "ग़्", "ġ"
+    sub "ज़्", "z"
+    sub "ड़्", "ṙ"
+    sub "ढ़्", "ṙh"
+    sub "फ़्", "f"
+  }
+  compose
+}
+

data/maps/un-kan-Kana-Latn-2016.imp

@@ -0,0 +1,214 @@
+metadata {
+  authority_id: ungegn
+  id: 2016
+  language: iso-639-2:kan
+  source_script: Kana
+  destination_script: Latn
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Kannada Romanization, 1972
+  url: https://www.eki.ee/wgrs/rom1_kn.pdf
+  creation_date: 1972
+  confirmation_date: 2016
+  description: |
+    The United Nations recommended system was approved in 1972 (II/11) and amended in 1977
+    (III/12), based on a report prepared by D. N. Sharma. The tables and their corrections were
+    published in volume II of the conference reports
+
+    There is no evidence of the use of the system either in India or in international cartographic
+    products.
+
+    Kannada uses an alphasyllabic script whereby each character represents a syllable rather than
+    one sound. Vowels and diphthongs are marked in two ways: as independent characters (used
+    syllable-initially) and in an abbreviated form, to denote vowels after consonants. The
+    romanization table is unambiguous. The system is mostly reversible but there may exist some
+    ambiguities in the romanization of vowels (independent vs. abbreviated characters) and
+    consonants (combinations with subscript consonants vs. character sequences).
+
+  notes:
+    - |
+      While most consonants have a diacritic in the upper right corner of the character (like ಕ),
+      some do not, e.g. ಖ kha, ಜ ja, ನ na, ಬ ba, ಲ la.
+    - |
+      Combinations with r as the first component are written by adding a special symbol after the
+      second consonant: ರ್ಗ rga.
+}
+
+tests {
+  test "ಕರ್ಣಾಟಕ", "karṇāṭaka"
+  test "ಬೆಂಗಳೂರು", "bĕṁgaḷūru"
+  test "ಮಹಾರಾಷ್ಟ್ರದ ಯಾವುದೇ ಪ್ರಕರಣದ ತನಿಖೆಗೆ ಇನ್ನು ಸಿಬಿಐ ಪಡೆಯಬೇಕು ಅನುಮತಿ", "mahārāṣhṭrada yāvude prakaraṇada tanikhĕgĕ innu sibiai paḍĕyabeku anumati"
+  test "ಹರಕು ಬಾಯಿ: ಈಶ್ವರಪ್ಪಗೆ ಶಾಸಕ ಯತ್ನಾಳ ತಿರುಗೇಟು", "haraku bāyi: īshvarappagĕ shāsaka yatnāḷa tirugeṭu"
+  test "ಹಾಥರಸ್‌ ಪ್ರಕರಣ: ೨೯ರಂದು ರಾಷ್ಟ್ರವ್ಯಾಪಿ ಪ್ರತಿಭಟನೆಗೆ ಮಹಿಳಾ ಸಂಘಟನೆಗಳ ಕರೆ", "hātharas prakaraṇa: 29raṁdu rāṣhṭravyāpi pratibhaṭanĕgĕ mahiḷā saṁghaṭanĕgaḷa karĕ"
+  test "ಪೊಲೀಸ್‌ ಮಕ್ಕಳ ಶಾಲೆ ಮುಚ್ಚುವ ಯತ್ನಕ್ಕೆ ಹೊರಟ್ಟಿ ತೀವ್ರ ವಿರೋಧ", "pŏlīs makkaḷa shālĕ muchchuva yatnakkĕ hŏraṭṭi tīvra virodha"
+  test "ಅಮೆರಿಕ ಅಧ್ಯಕ್ಷೀಯ ಚುನಾವಣೆ: ಟ್ರಂಪ್‌–ಬೈಡನ್‌ ಅಂತಿಮ ಮುಖಾಮುಖಿಗೆ ವೇದಿಕೆ ಸಿದ್ಧ", "amĕrika adhyakṣhīya chunāvaṇĕ: ṭraṁp–baiḍan aṁtima mukhāmukhigĕ vedikĕ siddha"
+  test "ಅಂಜನಾದ್ರಿ ಆಂಜನೇಯನ ದರ್ಶನ ಪಡೆದ ಪವರ್ ಸ್ಟಾರ್ ಪುನೀತ್ ರಾಜ್ ಕುಮಾರ್", "aṁjanādri āṁjaneyana darshana paḍĕda pavar sṭār punīt rāj kumār"
+  test "ಇನ್ನು ಹಿಂದೂ ದೇವಸ್ಥಾನದ ಧಾರ್ಮಿಕ ಕಾರ್ಯದಲ್ಲಿ ಭಾಗಿಯಾಗಿದ್ದಕ್ಕೆ ಮೋಯಿದ್ದೀನ್ ಬಾವಾಗೆ ಬೆದರಿಕೆ ಒಡ್ಡಲಾಗಿದೆ", "innu hiṁdū devasthānada dhārmika kāryadalli bhāgiyāgiddakkĕ moyiddīn bāvāgĕ bĕdarikĕ ŏḍḍalāgidĕ"
+  test "ಇದು ಮೋದಿ ದೇಶ - ದನ ತಿಂದು ಹೋದ್ರೆ ಹುಷಾರ್ : ದೇಗುಲಕ್ಕೆ ಹೋಗಿದ್ದ ಬಾವಾಗೆ ಬೆದರಿಕೆ", "idu modi desha - dana tiṁdu hodrĕ huṣhār : degulakkĕ hogidda bāvāgĕ bĕdarikĕ"
+}
+
+aliases {
+  def_alias characters_set1,   any("\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd")
+}
+
+stage {
+
+  # RULES
+  # to cover diacritic and vowel less consonants
+  sub "ಕ", "k", after: characters_set1
+  sub "ಖ", "kh", after: characters_set1
+  sub "ಗ", "g", after: characters_set1
+  sub "ಘ", "gh", after: characters_set1
+  sub "ಙ", "ṅ", after: characters_set1
+  sub "ಚ", "ch", after: characters_set1
+  sub "ಛ", "chh", after: characters_set1
+  sub "ಜ", "j", after: characters_set1
+  sub "ಝ", "jh", after: characters_set1
+  sub "ಞ", "ñ", after: characters_set1
+  sub "ಟ", "ṭ", after: characters_set1
+  sub "ಠ", "ṭh", after: characters_set1
+  sub "ಡ", "ḍ", after: characters_set1
+  sub "ಢ", "ḍh", after: characters_set1
+  sub "ಣ", "ṇ", after: characters_set1
+  sub "ತ", "t", after: characters_set1
+  sub "ಥ", "th", after: characters_set1
+  sub "ದ", "d", after: characters_set1
+  sub "ಧ", "dh", after: characters_set1
+  sub "ನ", "n", after: characters_set1
+  sub "ಪ", "p", after: characters_set1
+  sub "ಫ", "ph", after: characters_set1
+  sub "ಬ", "b", after: characters_set1
+  sub "ಭ", "bh", after: characters_set1
+  sub "ಮ", "m", after: characters_set1
+  sub "ಯ", "y", after: characters_set1
+  sub "ರ", "r", after: characters_set1
+  sub "ಲ", "l", after: characters_set1
+  sub "ಳ", "ḷ", after: characters_set1
+  sub "ವ", "v", after: characters_set1
+  sub "ಶ", "sh", after: characters_set1
+  sub "ಷ", "ṣh", after: characters_set1
+  sub "ಸ", "s", after: characters_set1
+  sub "ಹ", "h", after: characters_set1
+
+
+  # CHARACTERS
+  parallel {
+    sub "ಅ", "a"
+    sub "ಆ", "ā"
+    sub "ಇ", "i"
+    sub "ಈ", "ī"
+    sub "ಉ", "u"
+    sub "ಊ", "ū"
+    sub "ಋ", "ṛ"
+
+    sub "ಎ", "ĕ"
+    sub "ಏ", "e"
+    sub "ಐ", "ai"
+
+    sub "ಒ", "ŏ"
+    sub "ಓ", "o"
+    sub "ಔ", "au"
+
+    # Gutturals
+    sub "ಕ", "ka"
+    sub "ಖ", "kha"
+    sub "ಗ", "ga"
+    sub "ಘ", "gha"
+    sub "ಙ", "ṅa"
+
+    # Palatals
+    sub "ಚ", "cha"
+    sub "ಛ", "chha"
+    sub "ಜ", "ja"
+    sub "ಝ", "jha"
+    sub "ಞ", "ña"
+
+    # Cerebrals
+    sub "ಟ", "ṭa"
+    sub "ಠ", "ṭha"
+    sub "ಡ", "ḍa"
+    sub "ಢ", "ḍha"
+    sub "ಣ", "ṇa"
+
+    # Dentals
+    sub "ತ", "ta"
+    sub "ಥ", "tha"
+    sub "ದ", "da"
+    sub "ಧ", "dha"
+    sub "ನ", "na"
+
+    # Labials
+    sub "ಪ", "pa"
+    sub "ಫ", "pha"
+    sub "ಬ", "ba"
+    sub "ಭ", "bha"
+    sub "ಮ", "ma"
+
+    # Semivowels
+    sub "ಯ", "ya"
+    sub "ರ", "ra"
+    sub "ಲ", "la"
+    sub "ಳ", "ḷa"
+
+
+    sub "ವ", "va"
+
+    # Sibilants
+    sub "ಶ", "sha"
+    sub "ಷ", "ṣha"
+    sub "ಸ", "sa"
+
+
+    # Aspirate
+    sub "ಹ", "ha"
+
+
+    # Bisarga
+    sub "ಃ", "ḥ"
+
+    # Anusvāra
+    sub "ಂ", "ṁ"
+
+    sub "\u0cbc", "" #nukta
+
+    # Medials # Needed for connecting constants
+    sub "ಾ", "ā"
+    sub "ಿ", "i"
+    sub "ೀ", "ī"
+    sub "ು", "u"
+    sub "ೂ", "ū"
+    sub "ೃ", "ṛ"
+
+
+    sub "ೆ", "ĕ"
+    sub "ೇ", "e"
+    sub "ೈ", "ai"
+
+
+    sub "ೊ", "ŏ"
+    sub "ೋ", "o"
+    sub "ೌ", "au"
+
+
+    sub "्", ""
+    sub "़", ""
+    sub "್", "" # used for pronounciation without vowel
+    sub "‍", "" # no need for zero with joiner
+    sub "‌", "" # no need for zero with non joiner
+
+
+
+    # Digits
+
+    sub "೦", "0"
+    sub "೧", "1"
+    sub "೨", "2"
+    sub "೩", "3"
+    sub "೪", "4"
+    sub "೫", "5"
+    sub "೬", "6"
+    sub "೭", "7"
+    sub "೮", "8"
+    sub "೯", "9"
+  }
+
+  compose
+}