interscript-maps 2.4.3 → 2.5.0

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

@@ -0,0 +1,677 @@
+system "UN:hin-Deva:Latn:2016" {
+
+metadata {
+  authority_id un
+  id 2016
+  language iso-639-2:hin
+  source_script Deva
+  destination_script Latn
+  name Romanization of Hindi -- UNGEGN 4.0
+  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 {
+    note "      It is recommended that the vowel अ (a) should always be romanized except when it ends a\n      name. If a name ends with a consonant, the consonant should carry a sub-macron. Such\n      cases, however, will be very rare. For example, कानपुर Kānapur (not Kānapura), जगत्\n      Jagat."
+    note "      If each letter of a digraph or any two parts of a trigraph has a distinct independent sound\n      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 {
+   "दिल्ली" ->  "dillī"
+   "भारत" ->  "bhārat"
+   "परिपक्क" ->  "paripakk"
+   "जगत्" ->  "jagat"
+   "संख्या" ->  "saṁkhyā"
+   "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर" ->  "gaṁbhīr marījoṁ ke māmale meṁ bhārat dūsare naṁbar par"
+   "कोरोना अपडेट्स" ->  "koronā apaḍeṭs"
+   "सीडीसी चीफ का बयान अहम" ->  "sīḍīsī chīph kā bayān aham"
+   "गूगल प्ले स्टोर पर पेटीएम की वापसी" ->  "gūgal ple sṭor par peṭīem kī vāpasī"
+   "भारत में गैंबलिंग की इजाजत नहीं" ->  "bhārat meṁ gaiṁbaliṁg kī ijājat nahīṁ"
+   "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"
+   "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"
+
+  # Note: UN card expects this to start with an uppercase letter, but that would break other tests
+   "भारत" ->  "bhārat"
+   "दिल्ली" ->  "dillī"
+}
+
+
+aliases {
+  deva_characters_1 = any("\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d")
+}
+
+stage main {
+
+  # RULES
+  sub {
+    from "क" + maybe("=")
+    to "k"
+    after deva_characters_1
+  }
+  sub {
+    from "क"
+    to "k"
+    after boundary
+  }
+
+  sub {
+    from "ख" + maybe("=")
+    to "kh"
+    after deva_characters_1
+  }
+  sub {
+    from "ख"
+    to "kh"
+    after boundary
+  }
+
+  sub {
+    from "ग" + maybe("=")
+    to "g"
+    after deva_characters_1
+  }
+  sub {
+    from "ग"
+    to "g"
+    after boundary
+  }
+
+  sub {
+    from "घ" + maybe("=")
+    to "gh"
+    after deva_characters_1
+  }
+  sub {
+    from "घ"
+    to "gh"
+    after boundary
+  }
+
+  sub {
+    from "ङ" + maybe("=")
+    to "ṅ"
+    after deva_characters_1
+  }
+  sub {
+    from "ङ"
+    to "ṅ"
+    after boundary
+  }
+
+  sub {
+    from "च" + maybe("=")
+    to "ch"
+    after deva_characters_1
+  }
+  sub {
+    from "च"
+    to "ch"
+    after boundary
+  }
+
+  sub {
+    from "छ" + maybe("=")
+    to "chh"
+    after deva_characters_1
+  }
+  sub {
+    from "छ"
+    to "chh"
+    after boundary
+  }
+
+  sub {
+    from "ज" + maybe("=")
+    to "j"
+    after deva_characters_1
+  }
+  sub {
+    from "ज"
+    to "j"
+    after boundary
+  }
+
+  sub {
+    from "झ" + maybe("=")
+    to "jh"
+    after deva_characters_1
+  }
+  sub {
+    from "झ"
+    to "jh"
+    after boundary
+  }
+
+  sub {
+    from "ञ" + maybe("=")
+    to "ñ"
+    after deva_characters_1
+  }
+  sub {
+    from "ञ"
+    to "ñ"
+    after boundary
+  }
+
+  sub {
+    from "ट" + maybe("=")
+    to "ṭ"
+    after deva_characters_1
+  }
+  sub {
+    from "ट"
+    to "ṭ"
+    after boundary
+  }
+
+  sub {
+    from "ठ" + maybe("=")
+    to "ṭh"
+    after deva_characters_1
+  }
+  sub {
+    from "ठ"
+    to "ṭh"
+    after boundary
+  }
+
+  sub {
+    from "ड" + maybe("=")
+    to "ḍ"
+    after deva_characters_1
+  }
+  sub {
+    from "ड"
+    to "ḍ"
+    after boundary
+  }
+
+  sub {
+    from "ढ" + maybe("=")
+    to "ḍh"
+    after deva_characters_1
+  }
+  sub {
+    from "ढ"
+    to "ḍh"
+    after boundary
+  }
+
+  sub {
+    from "ण" + maybe("=")
+    to "ṇ"
+    after deva_characters_1
+  }
+  sub {
+    from "ण"
+    to "ṇ"
+    after boundary
+  }
+
+  sub {
+    from "त" + maybe("=")
+    to "t"
+    after deva_characters_1
+  }
+  sub {
+    from "त"
+    to "t"
+    after boundary
+  }
+
+  sub {
+    from "थ" + maybe("=")
+    to "th"
+    after deva_characters_1
+  }
+  sub {
+    from "थ"
+    to "th"
+    after boundary
+  }
+
+  sub {
+    from "द" + maybe("=")
+    to "d"
+    after deva_characters_1
+  }
+  sub {
+    from "द"
+    to "d"
+    after boundary
+  }
+
+  sub {
+    from "ध" + maybe("=")
+    to "dh"
+    after deva_characters_1
+  }
+  sub {
+    from "ध"
+    to "dh"
+    after boundary
+  }
+
+  sub {
+    from "न" + maybe("=")
+    to "n"
+    after deva_characters_1
+  }
+  sub {
+    from "न"
+    to "n"
+    after boundary
+  }
+
+  sub {
+    from "प" + maybe("=")
+    to "p"
+    after deva_characters_1
+  }
+  sub {
+    from "प"
+    to "p"
+    after boundary
+  }
+
+  sub {
+    from "फ" + maybe("=")
+    to "ph"
+    after deva_characters_1
+  }
+  sub {
+    from "फ"
+    to "ph"
+    after boundary
+  }
+
+  sub {
+    from "ब" + maybe("=")
+    to "b"
+    after deva_characters_1
+  }
+  sub {
+    from "ब"
+    to "b"
+    after boundary
+  }
+
+  sub {
+    from "भ" + maybe("=")
+    to "bh"
+    after deva_characters_1
+  }
+  sub {
+    from "भ"
+    to "bh"
+    after boundary
+  }
+
+  sub {
+    from "म" + maybe("=")
+    to "m"
+    after deva_characters_1
+  }
+  sub {
+    from "म"
+    to "m"
+    after boundary
+  }
+
+  sub {
+    from "य" + maybe("=")
+    to "y"
+    after deva_characters_1
+  }
+  sub {
+    from "य"
+    to "y"
+    after boundary
+  }
+
+  sub {
+    from "र" + maybe("=")
+    to "r"
+    after deva_characters_1
+  }
+  sub {
+    from "र"
+    to "r"
+    after boundary
+  }
+
+  sub {
+    from "ल" + maybe("=")
+    to "l"
+    after deva_characters_1
+  }
+  sub {
+    from "ल"
+    to "l"
+    after boundary
+  }
+
+  sub {
+    from "व" + maybe("=")
+    to "v"
+    after deva_characters_1
+  }
+  sub {
+    from "व"
+    to "v"
+    after boundary
+  }
+
+  sub {
+    from "श" + maybe("=")
+    to "sh"
+    after deva_characters_1
+  }
+  sub {
+    from "श"
+    to "sh"
+    after boundary
+  }
+
+  sub {
+    from "ष" + maybe("=")
+    to "ṣh"
+    after deva_characters_1
+  }
+  sub {
+    from "ष"
+    to "ṣh"
+    after boundary
+  }
+
+  sub {
+    from "स" + maybe("=")
+    to "s"
+    after deva_characters_1
+  }
+  sub {
+    from "स"
+    to "s"
+    after boundary
+  }
+
+  sub {
+    from "क़" + maybe("=")
+    to "q"
+    after deva_characters_1
+  }
+  sub {
+    from "क़"
+    to "q"
+    after boundary
+  }
+
+  sub {
+    from "ख़" + maybe("=")
+    to "ḳh"
+    after deva_characters_1
+  }
+  sub {
+    from "ख़"
+    to "ḳh"
+    after boundary
+  }
+
+  sub {
+    from "ग़" + maybe("=")
+    to "g"
+    after deva_characters_1
+  }
+  sub {
+    from "ग़"
+    to "g"
+    after boundary
+  }
+
+  sub {
+    from "ज़" + maybe("=")
+    to "z"
+    after deva_characters_1
+  }
+  sub {
+    from "ज़"
+    to "z"
+    after boundary
+  }
+
+  sub {
+    from "ड़" + maybe("=")
+    to "ṙ"
+    after deva_characters_1
+  }
+  sub {
+    from "ड़"
+    to "ṙ"
+    after boundary
+  }
+
+  sub {
+    from "ढ़" + maybe("=")
+    to "ṙh"
+    after deva_characters_1
+  }
+  sub {
+    from "ढ़"
+    to "ṙh"
+    after boundary
+  }
+
+  sub {
+    from "फ़" + maybe("=")
+    to "f"
+    after deva_characters_1
+  }
+  sub {
+    from "फ़"
+    to "f"
+    after boundary
+  }
+
+  sub {
+    from "ह" + maybe("=")
+    to "h"
+    after deva_characters_1
+  }
+  sub {
+    from "ह"
+    to "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"
+    sub "ॉ" "ā̆ "
+    sub "ि" "i"
+    sub "ी" "ī"
+    sub "ु" "u"
+    sub "ू" "ū"
+    sub "ृ" "ṛ"
+    sub "े" "e"
+    sub "ै" "ai"
+    sub "ो" "o"
+    sub "ौ" "au"
+
+
+    # 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
+}
+
+}