interscript-maps 2.0.5

data/maps/un-nep-Deva-Latn-2013.imp

@@ -0,0 +1,62 @@
+metadata {
+  authority_id: ungegn
+  id: 2013
+  language: iso-639-2:nep
+  source_script: Deva
+  destination_script: Latn
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Nepali Romanization, 1972
+  url: https://www.eki.ee/wgrs/v3_0/rom1_ne.pdf
+  creation_date: 1972
+  confirmation_date: 2013
+  description: |
+    The United Nations recommended system was approved in 1972 (II/11), based on a report
+    prepared by D. N. Sharma. The note on the system was published in volume II of the
+    conference report.
+
+    There is no evidence of the use of the system either in Nepal or in international cartographic
+    products. The resolution IV/17 (1982) recommended association, inter alia, with Nepal in
+    carrying out further studies on the system. In Nepal a system of romanization is employed by
+    the Nepal Survey Department (NSD). This system has been applied to names appearing on
+    national mapping, and it is also used in the Geographic Information Infrastructure Programme
+    (NGIIP).
+
+    Nepali (Nepālī) uses the alphasyllabic script Devanāgarī.
+
+  notes:
+
+    - In normal spelling ṙ and ṙh are not marked, instead dotless ड ḍa, ढ ḍha are used to denote these sounds.
+    - |
+      Ligatures may be formed with r as the first component: ~ह rha.
+}
+
+tests {
+  test "नेपाल", "nepāl"
+  test "नेपाल काठ्माडौं", "nepāl kāṭhmāḍauṁ"
+  test "लेखन", "lekhan"
+  test "मुद्रा", "mudrā"
+  test "प्रशंसा", "prashaṁsā"
+  test "अंक", "aṁk"
+  test "नेकपाले स्थगित स्थायी कमिटीको बैठक भदौ गते बोलाउने भएको", "nekapāle sthagit sthāyī kamiṭīko baiṭhak bhadau gate bolāune bhaeko"
+  test "न घर रह्यो, न परिवार", "n ghar rahyo, n parivār"
+  test "ढोरपाटनमा भुजीखोला बाढीपहिरोले अभिभावक गुमाएका बालबालिकाको बिचल्ली", "ḍhorapāṭanamā bhujīkholā bāḍhīpahirole abhibhāvak gumāekā bālabālikāko bichallī"
+  test "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो", "susmitākā kākā hemabahādur r kākīlāī pani pahirole bagāyo"
+  test "संविधान जारी भएसँगै सार्वजनिक प्रशासनमा नयाँ उत्साह आउने अपेक्षा थियो", "saṁvidhān jārī bhaesam̐gai sārvajanik prashāsanamā nayām̐ utsāh āune apekṣhā thiyo"
+  test "देशमा कोरोना संक्रमित र मृतकको संख्या हरेक दिन बढ्दो छ", "deshamā koronā saṁkramit r mṛtakako saṁkhyā harek din baḍhdo chh"
+  test "गाउँपालिकाका अध्यक्ष टिका गुरुङका अनुसार विष्णुदासलाई राजुले सुत्नका लागि बेलुका साथी लगेका थिए", "gāum̐pālikākā adhyakṣh ṭikā guruṅakā anusār viṣhṇudāsalāī rājule sutnakā lāgi belukā sāthī lagekā thie"
+  test "यो आयोजना गाउँपालिकाको केन्द्र तेल्लोकमा पर्छ", "yo āyojanā gāum̐pālikāko kendr tellokamā parchh"
+  test "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो", "susmitākā kākā hemabahādur r kākīlāī pani pahirole bagāyo"
+  test "चैत पहिलो साता घर आएका उनी लकडाउन भएपछि यतै रोकिए", "chait pahilo sātā ghar āekā unī lakaḍāun bhaepachhi yatai rokie"
+  test "काम गर्न जानेको हकमा रोजगारदाता कम्पनीको पत्रसँगै वडा र जिल्ला प्रशासनको सिफारिस अनिवार्य गरिएको छ", "kām garn jāneko hakamā rojagāradātā kampanīko patrasam̐gai vaḍā r jillā prashāsanako siphāris anivāry garieko chh"
+  test "म त पहाडको एउटा गाउँबाट उडेर तल झरेको सिमल भुवा हुँ", "m t pahāḍako euṭā gāum̐bāṭ uḍer tal jhareko simal bhuvā hum̐"
+  test "अचम्म, धेरैले चिन्ने र सहजै बुझ्ने खालको चलेकै कवि पो भएँ", "achamm, dheraile chinne r sahajai bujhne khālako chalekai kavi po bhaem̐"
+  test "कतिपय सन्दर्भ र राजनीतिक रूपमा फाइदा हुने कुरामा कवि घिमिरेले गर्ने गरेको टिप्पणी पनि नेपाली लेखकमाझ आलोचित हुन्थ्यो", "katipay sandarbh r rājanītik rūpamā phāidā hune kurāmā kavi ghimirele garne gareko ṭippaṇī pani nepālī lekhakamājh ālochit hunthyo"
+}
+
+dependency "un-nep-Deva-Latn-1972", as: devalatn
+
+stage {
+
+  run map.devalatn.stage.main
+
+}
+

data/maps/un-ori-Orya-Latn-1972.imp

@@ -0,0 +1,208 @@
+metadata {
+  authority_id: ungegn
+  id: 1972
+  language: iso-639-2:ori
+  source_script: Orya
+  destination_script: Latn
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Oriya Romanization, 1972
+  url: http://www.eki.ee/wgrs/v2_2/rom1_or.pdf
+  creation_date: 1972
+  confirmation_date: 2003
+  description: |
+    The United Nations recommended system was approved in 1972 (II/11), based on a report
+    prepared by D. N. Sharma. The note on the system was 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.
+
+    Oriya 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:
+    - Combinations with r as the first component are written with a special superscript symbol, e.g. ର୍କ rka.
+}
+
+tests {
+  test "ର୍କ", "rka"
+  test "ଓଡ଼ିଆ", "oṙiā"
+  test "ଓଡ଼ିଶା", "oṙishā"
+  test "ଭୁବନେଶ୍ୱର", "bhubaneshvara"
+  test "ଆଇପିଏଲ୍‌-୧୩: ଦିଲ୍ଲୀ କ୍ୟାପିଟାଲ୍ସକୁ ୮୮ ରନ୍‌ ପରାସ୍ତ କଲା ସନରାଇଜର୍ସ ହାଇଦ୍ରାବାଦ", "āipiel-13: dillī kyāpiṭālsaku 88 ran parāsta kalā sanarāijarsa hāidrābāda"
+  test "ପ୍ରେମ ସମ୍ପର୍କରେ ଭଟ୍ଟା: ରାଗରେ ପ୍ରେମିକାର ତଣ୍ଟି କାଟି ନିଜେ ବିଷ ପିଇଲା ପ୍ରେମିକ", "prema samparkare bhaṭṭā: rāgare premikāra taṇṭi kāṭi nije biṣha piilā premika"
+  test "ପ୍ରେମ ସମ୍ପର୍କରେ ଭଟ୍ଟା: ରାଗରେ ପ୍ରେମିକାର ତଣ୍ଟି କାଟି ନିଜେ ବିଷ ପିଇଲା ପ୍ରେମିକ", "prema samparkare bhaṭṭā: rāgare premikāra taṇṭi kāṭi nije biṣha piilā premika"
+  test "ହୋଟେଲ, ଲଜ୍‌ରେ ରୁମ୍‌ ମିଳୁନି: ନେତା‌ଙ୍କ ନାଁରେ ଆଗୁଆ ହୋଇଯାଇଛି ବୁକିଂ", "heāṭela, lajre rum miḷuni: netāṅka nāmre āguā heāiỵāichhhi bukiṃ"
+  test "ପର୍ଯ୍ୟଟକମାନଙ୍କ ନିମନ୍ତେ ନଭେମ୍ବର ୧ରୁ ଖୋଲିବ ଶିମିଳିପାଳ ଅଭୟାରଣ୍ୟ", "parỵyaṭakamānaṅka nimante nabhembara 1ru kholiba shimiḷipāḷa abhayāraṇya"
+  test "ପାରିବାରିକ ଅଶାନ୍ତିର କରୁଣ ପରିଣତି: କୂଅକୁ ଡେଇଁଲେ ମା’-ଝିଅ, ଝିଅ ମୃତ", "pāribārika ashāntira karuṇa pariṇati: kūaku ḍeimle mā’-jhia, jhia mṛta"
+  test "‘ଭ୍ରଷ୍ଟାଚାରର ବଂଶବାଦ’ ଏବେ ସାଜିଛି ଦେଶ ପାଇଁ ନୂଆ ସମସ୍ୟା; ପ୍ରଧାନମନ୍ତ୍ରୀ ମୋଦୀ", "‘bhraṣhṭāchārara baṃshabāda’ ebe sājichhhi desha pāim nūā samasyā; pradhānamantrī modī"
+  test "ପାହାଡ଼ି ଇଲାକାବାସୀଙ୍କ ଆଶାର ବତୀ ‘ପାର୍ବତୀ’", "pāhāṙi ilākābāsīṅka āshāra batī ‘pārbatī’"
+}
+
+aliases {
+  def_alias orya_chars_1, any("\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c")
+}
+
+stage {
+
+  # RULES
+  sub "କ", "k", after: orya_chars_1
+  sub "ଖ", "kh", after: orya_chars_1
+  sub "ଗ", "g", after: orya_chars_1
+  sub "ଘ", "gh", after: orya_chars_1
+  sub "ଙ", "ṅ", after: orya_chars_1
+  sub "ଚ", "ch", after: orya_chars_1
+  sub "ଛ", "chhh", after: orya_chars_1
+  sub "ଜ", "j", after: orya_chars_1
+  sub "ଝ", "jh", after: orya_chars_1
+  sub "ଞ", "ñ", after: orya_chars_1
+  sub "ଟ", "ṭ", after: orya_chars_1
+  sub "ଠ", "ṭh", after: orya_chars_1
+  sub "ଡ", "ḍ", after: orya_chars_1
+  sub "ଡ଼", "ṙ", after: orya_chars_1
+  sub "ଢ", "ḍh", after: orya_chars_1
+  sub "ଢ଼", "ṙh", after: orya_chars_1
+  sub "ଣ", "ṇ", after: orya_chars_1
+  sub "ତ", "t", after: orya_chars_1
+  sub "ଥ", "th", after: orya_chars_1
+  sub "ଦ", "d", after: orya_chars_1
+  sub "ଧ", "dh", after: orya_chars_1
+  sub "ନ", "n", after: orya_chars_1
+  sub "ପ", "p", after: orya_chars_1
+  sub "ଫ", "ph", after: orya_chars_1
+  sub "ବ", "b", after: orya_chars_1
+  sub "ଭ", "bh", after: orya_chars_1
+  sub "ମ", "m", after: orya_chars_1
+  sub "ଯ", "ỵ", after: orya_chars_1
+  sub "ୟ", "y", after: orya_chars_1
+  sub "ର", "r", after: orya_chars_1
+  sub "ଲ", "l", after: orya_chars_1
+  sub "ଳ", "ḷ", after: orya_chars_1
+  sub "ଶ", "sh", after: orya_chars_1
+  sub "ଷ", "ṣh", after: orya_chars_1
+  sub "ସ", "s", after: orya_chars_1
+  sub "ହ", "h", after: orya_chars_1
+  sub "କ୍ଷ", "kṣh", after: orya_chars_1
+
+
+  # CHARACTERS
+  parallel {
+    sub "ଅ", "a"
+    sub "ଆ", "ā"
+    sub "ଇ", "i"
+    sub "ଈ", "ī"
+    sub "ଉ", "u"
+    sub "ଊ", "ū"
+    sub "ଋ", "ṛ"
+    sub "ୠ", "ṝ"
+    sub "ଌ", "ḻ"
+    sub "ଏ", "e"
+    sub "ଐ", "ai"
+    sub "ଓ", "o"
+    sub "ୱ", "va"
+    sub "ଔ", "au"
+
+    # II. Consonants
+    # Gutturals
+    sub "କ", "ka"
+    sub "ଖ", "kha"
+    sub "ଗ", "ga"
+    sub "ଘ", "gha"
+    sub "ଙ", "ṅa"
+
+    # Palatals
+    sub "ଚ", "cha"
+    sub "ଛ", "chha"
+    sub "ଜ", "ja"
+    sub "ଝ", "jha"
+    sub "ଞ", "ña"
+
+    # Cerebrals
+    sub "ଟ", "ṭa"
+    sub "ଠ", "ṭha"
+    sub "ଡ", "ḍa"
+    sub "ଡ଼", "ṙa"
+    sub "ଢ", "ḍha"
+    sub "ଢ଼", "ṙha"
+    sub "ଣ", "ṇa"
+
+    # Dentals
+    sub "ତ", "ta"
+    sub "ଥ", "tha"
+    sub "ଦ", "da"
+    sub "ଧ", "dha"
+    sub "ନ", "na"
+
+    # Labials
+    sub "ପ", "pa"
+    sub "ଫ", "pha"
+    sub "ବ", "ba"
+    sub "ଭ", "bha"
+    sub "ମ", "ma"
+
+    # Semivowels
+    sub "ଯ", "ỵa"
+    sub "ୟ", "ya"
+    sub "ର", "ra"
+    sub "ଲ", "la"
+    sub "ଳ", "ḷa"
+
+    # Sibilants
+    sub "ଶ", "sha"
+    sub "ଷ", "ṣha"
+    sub "ସ", "sa"
+
+
+    # Aspirate
+    sub "ହ", "ha"
+
+    sub "କ୍ଷ", "kṣha"
+
+    # Chandrabindu
+    sub "ଁ", "m"
+
+    # Bisarga
+    sub "ଃ", "ḥ"
+
+    # Anusvāra
+    sub "ଂ", "ṃ"
+
+    # Medials # Needed for connecting constants
+
+    sub "ା", "ā"
+    sub "ି", "i"
+    sub "ୀ", "ī"
+    sub "ୁ", "u"
+    sub "ୂ", "ū"
+    sub "ୃ", "ṛ"
+    sub "େ", "e"
+    sub "ୈ", "ai"
+    sub "ୋ", "o"
+    sub "ୌ", "au"
+
+    sub "्", ""
+    sub "୍", ""
+    sub "़", ""
+    sub "଼", ""
+    sub "।", "."
+    sub "‍", "" # Used for joining
+    sub "‌", "" # Used for non joining
+
+    # Numbers
+
+    sub "୦", "0"
+    sub "୧", "1"
+    sub "୨", "2"
+    sub "୩", "3"
+    sub "୪", "4"
+    sub "୫", "5"
+    sub "୬", "6"
+    sub "୭", "7"
+    sub "୮", "8"
+    sub "୯", "9"
+  }
+
+  compose
+}

data/maps/un-pan-Guru-Latn-1972.imp

@@ -0,0 +1,321 @@
+metadata {
+  authority_id: un
+  id: 1972
+  language: iso-639-2:pan
+  source_script: Guru
+  destination_script: Latn
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Panjabi Romanization Version 4.0
+  url: https://www.eki.ee/wgrs/rom1_pa.htm
+  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 reports1,2.
+
+    There is no evidence of the use of the system either in India or in international cartographic products.
+
+    Punjabi (Panjābī) in India uses an alphasyllabic script (Gurmukhi) 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 exist some ambiguities in the romanization of vowels (independent vs. abbreviated characters) and
+    consonants (combinations with subscript consonants vs. character sequences).
+
+    References
+
+    Second United Nations Conference on the Standardization of Geographical Names. London, 10–31 May 1972. Vol. II. Technical papers.
+    United Nations. New York 1974, pp. 136–138.
+
+    Third United Nations Conference on the Standardization of Geographical Names. Athens, 17 August – 7 September 1977. Vol. II,
+    Technical papers, pp. 393 etc.
+
+
+
+  notes:
+    - |
+      These characters are used in combination with abbreviated vowel characters: ਉ u, ਊ ū, ਅ a, ਆ ā, ਐ ai, ਔ au, ਇ i, ਈ ī, ਏ e; exceptional variation: ਓ o.
+    - |
+      Dotted variants of the characters: ਸ਼ sha, ਖ਼ ḳha, ਗ਼ g̣a, ਜ਼ za, ਫ਼ fa.
+    - |
+      (ੰ) Used if it is preceded by short vowels (a, i, u) and ū, excluding the independent vowel character ਉ (u, ū), e.g. ਸੰਗ saṁg, ਸਿੰਗ siṁg, ਬੁੰਦਾ buṁdā, ਬੂੰਦ būṁd, ਇੰਜਨ iṁjan.
+    - |
+      (ਂ) Used in all other occasions, e.g. ਝੋਂਕਾ jhoṁkā.
+    - |
+      (ੱ) Marks doubling of the following consonant: ਨਿੱਕਾ nikkā, ਲੱਭਣਾ labhbhṇā, ਕੁੱਤਾ kuttā, ਹਿੱਸਾ hissā, ਲੱਮਾ lammā.
+    - |
+      Absence of the inherent vowel (-a) is not marked in the spelling in any way except for the combinations
+      with subscript characters and those which are doubled by ੱ (adhaka).
+}
+
+tests {
+  test "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ", "paṁzāba 'cha vadha rihā khaḳhudakusḳhīāṁ dā rujhāna"
+  test "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ", "lakkha toṁ pāra puzzā sragarama kesāṁ dā aṁkaṙā, dillī 'cha do lakkha toṁ pāra inaphaikaṭiḍa"
+  test "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ", "parivāraka smassiāvāṁ ate viāh vī hai hora ahima kārana"
+  test "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ", "maradāṁ 'cha auratāṁ nāloṁ vaddha hai khaḳhudakusḳhī dā rujhāna"
+  test "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ", "rāsṭarī paddhara 'te paṁzāba dī sthitī kāphaḳhī sūbiāṁ toṁ bihtara"
+  test "ਚੀਨੀ ਸੈਨਾ ਨੇ ਲਾਪਤਾ ਅਰੁਣਾਚਲ ਦੇ 5 ਨੌਜਵਾਨਾਂ ਬਾਰੇ ਦੱਸਿਆ", "chīnī sainā ne lāpatā aruṇāchala de 5 naujavānāṁ bāre dassiā"
+  test "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ", "sākharatā de māmale 'cha des 'cha 7veṁ naṁbara 'te paṁzāba"
+  test "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ", "dillī kameṭī de maiṁbara sṁṭī ne akālī dala toṁ dittā astīphaḳhā"
+  test "੧੦੨ ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ", "102 hora koronā pājaḳhīṭiva marījaḳhāṁ dī pusṭī, ika dī mauta"
+  test "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ", "sṙaka hādase daurāna ika dī mauta"
+}
+
+stage {
+
+  # RULES
+    sub "ਕ", "k", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਖ", "kh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਖ਼"), "ḳh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਗ", "g", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਗ਼"), "g̣", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਘ", "gh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਙ", "ṅ", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਚ", "ch", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਛ", "chh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਜ਼"), "z", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਜ", "j", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਝ", "jh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਞ", "ñ", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਟ", "ṭ", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਠ", "ṭh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਡ", "ḍ", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਢ", "ḍh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਣ", "ṇ", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਤ", "t", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਥ", "th", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਦ", "d", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਧ", "dh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਨ", "n", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਪ", "p", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਫ", "ph", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਫ਼"), "f", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਬ", "b", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਭ", "bh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਮ", "m", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਯ", "y", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਰ", "r", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਲ", "l", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਲੵ"), "l", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਲ਼"), "l", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਵ", "v", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ੜ", "ṙ", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਸ", "s", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਸ਼", "sh", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਹ", "h", not_before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+
+    sub "ਕ", "kk", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਖ", "kkh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਖ਼"), "ḳḳh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਗ", "gg", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਗ਼"), "gg̣", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਘ", "ggh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਙ", "ṅṅ", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਚ", "cch", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਛ", "cchh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਜ਼"), "zz", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਜ", "jj", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਝ", "jjh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਞ", "ññ", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਟ", "ṭṭ", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਠ", "ṭṭh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਡ", "ḍḍ", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਢ", "ḍḍh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਣ", "ṇṇ", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਤ", "tt", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਥ", "tth", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਦ", "dd", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਧ", "ddh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਨ", "nn", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਪ", "pp", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਫ", "pph", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਫ਼"), "ff", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਬ", "bb", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਭ", "bbh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਮ", "mm", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਯ", "yy", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਰ", "rr", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਲ", "ll", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਲੵ"), "ll", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub any("ਲ਼"), "ll", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਵ", "vv", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ੜ", "ṙṙ", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਸ", "ss", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਸ਼", "ssh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+    sub "ਹ", "hh", before: "ੱ", after: any("\u0a3e\u0a3f\u0a40\u0a41\u0a42\u0a47\u0a48\u0a4b\u0a4c\u0a4d")
+
+
+  # CHARACTERS
+  parallel {
+
+    # I. Vowels and Diphthongs (see Note 1)
+    sub "ਅ", "a"
+    sub "ਆ", "ā"
+    sub "ਇ", "i"
+    sub "ਈ", "ī"
+    sub "ਉ", "u"
+    sub "ਊ", "ū"
+    sub "ਏ", "e"
+    sub "ਐ", "ai"
+    sub "ਓ", "o"
+    sub "ਔ", "au"
+
+    sub "ਾ", "ā"
+    sub "ਿ", "i"
+    sub "ੀ", "ī"
+    sub "ੁ", "u"
+    sub "ੂ", "ū"
+    sub "ੇ", "e"
+    sub "ੈ", "ai"
+    sub "ੋ", "o"
+    sub "ੌ", "au"
+
+    # II. Consonants
+    sub "ਕ", "ka"
+    sub "ਖ", "kha"
+    sub "ਖ਼", "ḳha"
+    sub "ਗ", "ga"
+    sub "ਗ਼", "g̣a"
+    sub "ਘ", "gha"
+    sub "ਙ", "ṅa"
+    sub "ਚ", "cha"
+    sub "ਛ", "chha"
+    sub "ਜ਼", "za"
+    sub "ਜ", "ja"
+    sub "ਝ", "jha"
+    sub "ਞ", "ña"
+    sub "ਟ", "ṭa"
+    sub "ਠ", "ṭha"
+    sub "ਡ", "ḍa"
+    sub "ਢ", "ḍha"
+    sub "ਣ", "ṇa"
+    sub "ਤ", "ta"
+    sub "ਥ", "tha"
+    sub "ਦ", "da"
+    sub "ਧ", "dha"
+    sub "ਨ", "na"
+    sub "ਪ", "pa"
+    sub "ਫ", "pha"
+    sub "ਫ਼", "fa"
+    sub "ਬ", "ba"
+    sub "ਭ", "bha"
+    sub "ਮ", "ma"
+    sub "ਯ", "ya"
+    sub "ਰ", "ra"
+    sub "ਲ", "la"
+    sub "ਲੵ", "la"
+    sub "ਲ਼", "la"
+    sub "ਵ", "va"
+    sub "ੜ", "ṙa"
+    sub "ਸ", "s"
+    sub "ਸ਼", "sha"
+    sub "ਹ", "h"
+    sub "ਂ", "ṁ"
+    sub "ੰ", "ṁ"
+
+    # Adhik character doubling of the following consonant[Note 5]
+    sub "ੱਕ", "kka"
+    sub "ੱਖ", "kkha"
+    sub "ੱਖ਼", "ḳḳha"
+    sub "ੱਗ", "gga"
+    sub "ੱਗ਼", "gg̣a"
+    sub "ੱਘ", "ggha"
+    sub "ੱਙ", "ṅṅa"
+    sub "ੱਚ", "ccha"
+    sub "ੱਛ", "cchha"
+    sub "ੱਜ਼", "zza"
+    sub "ੱਜ", "jja"
+    sub "ੱਝ", "jjha"
+    sub "ੱਞ", "ñña"
+    sub "ੱਟ", "ṭṭa"
+    sub "ੱਠ", "ṭṭha"
+    sub "ੱਡ", "ḍḍa"
+    sub "ੱਢ", "ḍḍha"
+    sub "ੱਣ", "ṇṇa"
+    sub "ੱਤ", "tta"
+    sub "ੱਥ", "ttha"
+    sub "ੱਦ", "dda"
+    sub "ੱਧ", "ddha"
+    sub "ੱਨ", "nna"
+    sub "ੱਪ", "ppa"
+    sub "ੱਫ", "ppha"
+    sub "ੱਫ਼", "ffa"
+    sub "ੱਬ", "bba"
+    sub "ੱਭ", "bbha"
+    sub "ੱਮ", "mma"
+    sub "ੱਯ", "yya"
+    sub "ੱਰ", "rra"
+    sub "ੱਲ", "lla"
+    sub "ੱਲੵ", "lla"
+    sub "ੱਲ਼", "lla"
+    sub "ੱਵ", "vva"
+    sub "ੱੜ", "ṙṙa"
+    sub "ੱਸ", "ss"
+    sub "ੱਸ਼", "ssha"
+    sub "ੱਹ", "hh"
+
+    # Adhik character doubling of the following consonant and ends with ੍ [Note 5]
+    sub "ੱਕ੍", "kk"
+    sub "ੱਖ੍", "kkh"
+    sub "ੱਖ਼੍", "ḳḳh"
+    sub "ੱਗ੍", "gg"
+    sub "ੱਗ਼੍", "gg̣"
+    sub "ੱਘ੍", "ggh"
+    sub "ੱਙ੍", "ṅṅ"
+    sub "ੱਚ੍", "cch"
+    sub "ੱਛ੍", "cchh"
+    sub "ੱਜ਼੍", "zz"
+    sub "ੱਜ੍", "jj"
+    sub "ੱਝ੍", "jjh"
+    sub "ੱਞ੍", "ññ"
+    sub "ੱਟ੍", "ṭṭ"
+    sub "ੱਠ੍", "ṭṭh"
+    sub "ੱਡ੍", "ḍḍ"
+    sub "ੱਢ੍", "ḍḍh"
+    sub "ੱਣ੍", "ṇṇ"
+    sub "ੱਤ੍", "tt"
+    sub "ੱਥ੍", "tth"
+    sub "ੱਦ੍", "dd"
+    sub "ੱਧ੍", "ddh"
+    sub "ੱਨ੍", "nn"
+    sub "ੱਪ੍", "pp"
+    sub "ੱਫ੍", "pph"
+    sub "ੱਫ਼੍", "ff"
+    sub "ੱਬ੍", "bb"
+    sub "ੱਭ੍", "bbh"
+    sub "ੱਮ੍", "mm"
+    sub "ੱਯ੍", "yy"
+    sub "ੱਰ੍", "rr"
+    sub "ੱਲ੍", "ll"
+    sub "ੱਲੵ੍", "ll"
+    sub "ੱਲ਼੍", "ll"
+    sub "ੱਵ੍", "vv"
+    sub "ੱੜ੍", "ṙṙ"
+    sub "ੱਸ੍", "ss"
+    sub "ੱਸ਼੍", "ssh"
+    sub "ੱਹ੍", "hh"
+
+
+    # III. Subscript consonant characters
+    sub "੍ਹ", "-h"
+    sub "੍ਵ", "-v"
+    sub "੍ਰ", "-r"
+    sub "੍ਯ", "-y"
+
+    sub "੍", ""
+    sub "ੱ", ""
+    sub "਼", ""
+
+    # digits
+    sub "੦", "0"
+    sub "੧", "1"
+    sub "੨", "2"
+    sub "੩", "3"
+    sub "੪", "4"
+    sub "੫", "5"
+    sub "੬", "6"
+    sub "੭", "7"
+    sub "੮", "8"
+    sub "੯", "9"
+  }
+  compose
+}