interscript-maps 2.4.2 → 2.5.0

data/maps/alalc-ori-Orya-Latn-1997.isc

@@ -0,0 +1,397 @@
+system "ALA-LC:ori-Orya:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:ori
+  source_script Orya
+  destination_script Latn
+  name Romanization Table -- Oriya (1997)
+  url http://catdir.loc.gov/catdir/cpso/romanization/oriya.pdf
+  creation_date 1997
+  description {    ALA-LC Romanization table for Oriya
+  }
+
+  notes {
+    note "      Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for vowels following a\n      consonant can be found in grammars; no distinction between the two is made in transliteration."
+    note "      The vowel a is implicit after all consonants and consonant clusters and is supplied in\n      transliteration, with the following exceptions:\n      a) when another vowel is indicated by its appropriate sign; and\n      b) when the absence of any vowel is indicated by the subscript sign ( ୍ ) called hasanta."
+    note "      ବ is used both as a labial and as a semivowel. When it occurs as the second consonant of a\n      consonant cluster, it is transliterated va. When ବ is doubled, it is transliterated bba."
+    note "      Exception: Anusvāra is transliterated by:\n        a) ṅ before gutturals,\n        b) ñ before palatals,\n        c) ṇ before cerebrals,\n        d) n before dentals, and\n        e) m before labials."
+    note "      Candrabindu before guttural, palatal, cerebral, and dental occlusives is transliterated n̐.\n      Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is\n      transliterated m̐."
+    note "When doubled, abagraha is transliterated by two apostrophes ( ’’ )."
+  }
+}
+
+tests {
+   "ର୍କ" ->  "rka"
+   "ଓଡ଼ିଆ" ->  "oṙiā"
+   "ଓଡ଼ିଶା" ->  "oṙiśā"
+   "ଭୁବନେଶ୍ୱର" ->  "bhubaneśwara"
+   "ଆଇପିଏଲ୍‌-୧୩: ରୟାଲ ଚ୍ୟାଲେଞ୍ଜର୍ସ ବାଙ୍ଗାଲୋରକୁ ୫ ଓ୍ୱିକେଟରେ ପରାସ୍ତ କଲା ମୁମ୍ବାଇ ଇଣ୍ଡିଆନ୍ସ" ->  "āipiel-13: raẏāla cẏāleñjarsa bāṅgāloraku 5 obikeṭare parāsta kalā mumbāi iṇḍiānsa"
+   "ଓଡ଼ିଶା ସିଭିଲ ସର୍ଭିସେସ୍‌ ମେନ୍‌ ପରୀକ୍ଷା ଡିସେମ୍ବରରେ, ଜାଣନ୍ତୁ କେଉଁ ବିଷୟର ପରୀକ୍ଷା କେବେ" ->  "oṙiśā sibhila sarbhises men parīkshā ḍisembarare, jāṇantu keum̐ bishaẏara parīkshā kebe"
+   "ଗଞ୍ଜାମରେ କୋଭିଡ଼ ମୃତ୍ୟୁ ୨୨୮ରେ ପହଞ୍ଚିଲା" ->  "gañjāmare keābhiṙa mṛtẏu 228re pahañcilā"
+   "ଭାରତ ମହାସାଗର ଦ୍ବୀପରାଷ୍ଟ୍ର ଶ୍ରୀଲଙ୍କା ଓ ମାଳଦ୍ବୀପରେ ପମ୍ପିଓଙ୍କ ଚୀନ୍‌ବିରୋଧୀ ଅଭିଯାନ" ->  "bhārata mahāsāgara dbīparāshṭra śrīlaṅkā o māḷadbīpare pampioṅka cīnbireādhī abhiyāna"
+   "କଟକ ସହରରୁ ଆଜି ୩୯ କରୋନା ପଜିଟିଭ୍‌ ଚିହ୍ନଟ, ସ୍ଥାନୀୟ ଅଂଚଳରୁ ୨୪ ଜଣ ଆକ୍ରାନ୍ତ" ->  "kaṭaka sahararu āji 39 karonā pajiṭibh cihnaṭa, sthānīẏa aṃcaḷaru 24 jaṇa ākrānta"
+   "ବିଧାୟକ ସୌମ୍ୟରଂଜନଙ୍କ ମାରାଥନ ପ୍ରଚାର: ‘ଦ୍ୱିତୀୟବାର ସୁଯୋଗ ମିଳିଛି, ବୁଝି ବିଚାରି ଭୋଟ ଦିଅ’" ->  "bidhāẏaka seୗmẏaraṃjanaṅka mārāthana pracāra: ‘dbitīẏabāra suyeāga miḷichi, bujhi bicāri bheāṭa dia’"
+   "ଅଣ୍ଡା ବିଗାଡ଼ିଛି ପୁଷ୍ଟିକର ଖାଦ୍ୟ ଯୋଜନା ଅଙ୍କ" ->  "aṇḍā bigāṙichi pushṭikara khādẏa yeājanā aṅka"
+   "ପଥରଗଡ଼ ମଦ ମୃତ୍ୟୁ ମାମଲା : ଠିକାଦାର ସହ ବନ୍ଧାହେଲେ ୪" ->  "patharagaḍa mada mṛtẏu māmalā : ṭhikādāra saha bandhāhele 4"
+   "ତିର୍ତ୍ତୋଲର ବିକାଶ ନେଇ ବିଷ୍ଣୁବାବୁ ମୋତେ ବହୁ ବାର ଭେଟୁଥିଲେ: ନବୀନ" ->  "tirtteālara bikāśa nei bishṇubābu mote bahu bāra bheṭuthile: nabīna"
+}
+
+aliases {
+  cons_or_cluster = any("\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c")
+}
+
+stage main {
+
+  # RULES
+  # Rule II
+  sub {
+    from "କ"
+    to "k"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଖ"
+    to "kh"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଗ"
+    to "g"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଘ"
+    to "gh"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଙ"
+    to "ṅ"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଚ"
+    to "c"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଛ"
+    to "ch"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଜ"
+    to "j"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଝ"
+    to "jh"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଞ"
+    to "ñ"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଟ"
+    to "ṭ"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଠ"
+    to "ṭh"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଡ"
+    to "ḍ"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଢ"
+    to "ḍh"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଣ"
+    to "ṇ"
+    after cons_or_cluster
+  }
+  sub {
+    from "ତ"
+    to "t"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଥ"
+    to "th"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଦ"
+    to "d"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଧ"
+    to "dh"
+    after cons_or_cluster
+  }
+  sub {
+    from "ନ"
+    to "n"
+    after cons_or_cluster
+  }
+  sub {
+    from "ପ"
+    to "p"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଫ"
+    to "ph"
+    after cons_or_cluster
+  }
+  sub {
+    from "ବ"
+    to "b"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଭ"
+    to "bh"
+    after cons_or_cluster
+  }
+  sub {
+    from "ମ"
+    to "m"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଯ"
+    to "y"
+    after cons_or_cluster
+  }
+  sub {
+    from "ୟ"
+    to "ẏ"
+    after cons_or_cluster
+  }
+  sub {
+    from "ର"
+    to "r"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଲ"
+    to "l"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଳ"
+    to "ḷ"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଶ"
+    to "ś"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଷ"
+    to "sh"
+    after cons_or_cluster
+  }
+  sub {
+    from "ସ"
+    to "s"
+    after cons_or_cluster
+  }
+  sub {
+    from "ହ"
+    to "h"
+    after cons_or_cluster
+  }
+  sub {
+    from "ୱ"
+    to "b"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଡ଼"
+    to "ṙ"
+    after cons_or_cluster
+  }
+  sub {
+    from "ଢ଼"
+    to "ṙh"
+    after cons_or_cluster
+  }
+
+  # Rule III
+  sub {
+    from "ବ"
+    to "bba"
+    after any("\u0b2c")
+  }
+  # Rule IV
+  sub {
+    from "\u0902"
+    to "ṅ"
+    after any("କଖଗଘଙ")
+  }
+  sub {
+    from "\u0902"
+    to "ñ"
+    after any("ଚଛଜଝଞ")
+  }
+  sub {
+    from "\u0902"
+    to "ṇ"
+    after any("ଟଠଡଢଣ")
+  }
+  sub {
+    from "\u0902"
+    to "n"
+    after any("ତଥଦଧନ")
+  }
+  # Rule V
+  sub {
+    from "\u0b01"
+    to "m̐"
+    after any("ପଫବଭମଯୟରଲଳଶଷସହଅଆଇଈଉଊଋୠଌଏଐଓଔ")
+  }
+  sub {
+    from "\u0b01"
+    to "m̐"
+    after boundary
+  }
+
+
+  # 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 "ଔ" "au"
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "କ" "ka"
+    sub "ଖ" "kha"
+    sub "ଗ" "ga"
+    sub "ଘ" "gha"
+    sub "ଙ" "ṅa"
+
+    # Palatals
+    sub "ଚ" "ca"
+    sub "ଛ" "cha"
+    sub "ଜ" "ja"
+    sub "ଝ" "jha"
+    sub "ଞ" "ña"
+
+    # Cerebrals
+    sub "ଟ" "ṭa"
+    sub "ଠ" "ṭha"
+    sub "ଡ" "ḍa"
+    sub "ଢ" "ḍha"
+    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" "ya"
+    sub "ୟ" "ẏa"
+    sub "ର" "ra"
+    sub "ଲ" "la"
+    sub "ଳ" "ḷa"
+
+    # Sibilants
+    sub "ଶ" "śa"
+    sub "ଷ" "sha"
+    sub "ସ" "sa"
+
+
+    # Aspirate
+    sub "ହ" "ha"
+
+    # Chandrabindu
+    sub "ଁ" "n̐"
+
+    # Bisarga
+    sub "ଃ" "ḥ"
+
+    # Anusvāra
+    sub "ଂ" "ṃ"
+
+    # Abagraha
+    sub "ଽ" "’"
+
+    # 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 "‍" ""
+    sub "‌" ""
+
+    #Absent but used
+    sub "ୱ" "wa"
+    sub "ଡ଼" "ṙa"
+    sub "ଢ଼" "ṙha"
+
+    # 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/alalc-ori-Orya-Latn-2011.isc

@@ -0,0 +1,46 @@
+system "ALA-LC:ori-Orya:Latn:2011" {
+
+metadata {
+  authority_id alalc
+  id 2011
+  language iso-639-2:ori
+  source_script Orya
+  destination_script Latn
+  name Romanization Table -- Oriya (2011)
+  url https://www.loc.gov/catdir/cpso/romanization/oriya.pdf
+  creation_date 2011
+  description {    ALA-LC Romanization table for Oriya
+  }
+
+  notes {
+    note "      Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for vowels following a\n      consonant can be found in grammars; no distinction between the two is made in transliteration."
+    note "      The vowel a is implicit after all consonants and consonant clusters and is supplied in\n      transliteration, with the following exceptions:\n      a) when another vowel is indicated by its appropriate sign; and\n      b) when the absence of any vowel is indicated by the subscript sign ( ୍ ) called hasanta."
+    note "      ବ is used both as a labial and as a semivowel. When it occurs as the second consonant of a\n      consonant cluster, it is transliterated va. When ବ is doubled, it is transliterated bba."
+    note "      Exception: Anusvāra is transliterated by:\n        a) ṅ before gutturals,\n        b) ñ before palatals,\n        c) ṇ before cerebrals,\n        d) n before dentals, and\n        e) m before labials."
+    note "      Candrabindu before guttural, palatal, cerebral, and dental occlusives is transliterated n̐.\n      Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is\n      transliterated m̐."
+    note "When doubled, abagraha is transliterated by two apostrophes ( ’’ )."
+  }
+}
+
+tests {
+   "ବିହାର ନିର୍ବାଚନ: ସନ୍ଧ୍ୟା ୬ଟା ସୁଦ୍ଧା ୫୩.୫୪ ପ୍ରତିଶତ ମତଦାନ" ->  "bihāra nirbācana: sandhẏā 6ṭā suddhā 53.54 pratiśata matadāna"
+   "ଡିସେମ୍ବର ସୁଦ୍ଧା ପ୍ରସ୍ତୁତ ହୋଇଯିବ ଅକ୍ସଫୋର୍ଡ କରୋନାଭାଇରସ୍ ଟିକା: ଅଦର ପୁନାୱାଲା" ->  "ḍisembara suddhā prastuta heāiyiba aksapheārḍa kareānābhāiras ṭikā: adara punābālā"
+   "କରୋନା ଆକ୍ରାନ୍ତ ହେଲେ କେନ୍ଦ୍ରମନ୍ତ୍ରୀ ସ୍ମୃତି ଇରାନୀ" ->  "karonā ākrānta hele kendramantrī smṛti irānī"
+   "ଆମେରିକା ଉପରେ ଉତ୍‌କ୍ଷିପ୍ତ ହୋଇ ଚୀନ୍ କହିଲା: ଭାରତ ସହ ଆମର ସୀମା ବିବାଦ ଦ୍ବିପାକ୍ଷିକ ମାମଲା" ->  "āmerikā upare utkshipta heāi cīn kahilā: bhārata saha āmara sīmā bibāda dbipākshika māmalā"
+   "ପରଲୋକରେ ଦକ୍ଷିଣ କୋରିଆର ସବୁଠୁ ଧନୀବ୍ୟକ୍ତି ‘ସାମ୍‌ସଙ୍ଗ୍’ ଅଧ୍ୟକ୍ଷ ଲି କୁନ୍-ହି; ଛାଡ଼ିଯାଇଛନ୍ତି ୨୧ ବିଲିୟନ୍ ଡଲାର୍‌ର ସାମ୍ରାଜ୍ୟ" ->  "paraleākare dakshiṇa keāriāra sabuṭhu dhanībẏakti ‘sāmsaṅg’ adhẏaksha li kun-hi; chāṙiyāichanti 21 biliẏan ḍalārra sāmrājẏa"
+   "ଉପନିର୍ବାଚନ ପାଇଁ ବାଲେଶ୍ୱରରେ ବିଜେଡିର ସମାବେଶ। (ଫଟୋ: ମନୋଜ ବିଶ୍ୱାଳ)" ->  "upanirbācana pāim̐ bāleśwarare bijeḍira samābeśa. (phaṭo: manoja biśbāḷa)"
+   "ନୂଆପଲ୍ଲୀ ଦୁର୍ଗାପୂଜା ମଣ୍ଡପ ବାହାରେ ମା’ଙ୍କୁ ପୂଜାର୍ଚ୍ଚନା କରୁଛନ୍ତି ଭକ୍ତ। (ଫଟୋ: ବିଭୂତି)" ->  "nūāpallī durgāpūjā maṇḍapa bāhāre mā’ṅku pūjārccanā karuchanti bhakta. (phaṭo: bibhūti)"
+   "ମା ଶାରଳାଙ୍କ ପୀଠରେ ଦଶମୀ ପୂଜା। (ଫଟୋ: ସୋମନାଥ, ଜଗତସିଂହପୁର ଟାଉନ୍‌)" ->  "mā śāraḷāṅka pīṭhare daśamī pūjā. (phaṭo: somanātha, jagatasiṃhapura ṭāun)"
+   "ଆଜି ବିହାରରେ ପ୍ରଥମ ପର୍ଯ୍ୟାୟ ଭୋଟ, ମହାମେଣ୍ଟ-ଏନ୍‌ଡିଏ କଡ଼ା ଟକ୍କର" ->  "āji bihārare prathama paryẏāẏa bheāṭa, mahāmeṇṭa-enḍie kaṙā ṭakkara"
+   "ନିର୍ବାଚନ ପ୍ରଚାରରୁ ଫେରି ନିଜ ଅଭିଜ୍ଞତା ବଖାଣି ଅମିଷା କହିଲେ, ‘କୌଣସି ପରିସ୍ଥିତିରେ ମୋର ସହିତ ଦୁଷ୍କର୍ମ ହେବାର ଆଶଙ୍କା ରହିଥିଲା’" ->  "nirbācana pracāraru pheri nija abhijñatā bakhāṇi amishā kahile, ‘keୗṇasi paristhitire meāra sahita dushkarma hebāra āśaṅkā rahithilā’"
+   "ବ୍ଲୁ ଫ୍ଲାଗ ବିଚ୍‌ରେ ଅଘଟଣ: ମା’ ଆଗରେ ସମୁଦ୍ରରେ ଭାସିଗଲେ ପୁଅ, ଖୋଜିବା ପାଇଁ ଲାଇଫଗାର୍ଡ ଟିମ୍‌ ନିୟୋଜିତ" ->  "blu phlāga bicre aghaṭaṇa: mā’ āgare samudrare bhāsigale pua, kheājibā pāim̐ lāiphagārḍa ṭim niẏeājita"
+}
+
+dependency "alalc-ori-Orya-Latn-1997" as oryalatn
+
+stage main {
+
+  run  map.oryalatn.stage.main
+
+}
+}

data/maps/alalc-pan-Guru-Latn-1997.isc

@@ -0,0 +1,254 @@
+system "ALA-LC:pan-Guru:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:pan
+  source_script Guru
+  destination_script Latn
+  name Romanization Table -- Panjabi (1997)
+  url http://catdir.loc.gov/catdir/cpso/romanization/panjabi.pdf
+  creation_date 1997
+  description {    ALA-LC Romanization table for Panjabi
+  }
+
+  notes {
+
+    note "Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for\n vowels following a consonant can be found in grammars; no distinction between the two is\n made in transliteration."
+
+    note "      The vowel a is implicit after consonant clusters and may be implicit after consonants except\n      when they are final or when another vowel is indicated by its appropriate sign. The cases in\n      which the vowel a is implicit, however, can be determined only from a knowledge of the\n      language or from suitable reference sources. In such cases the a is supplied in transliteration."
+
+    note "The dotted letters (ਸ਼ ਖ਼ ਗ਼ ਜ਼ ਫ਼ ਲ਼) are used in Urdu words."
+
+    note "      Exception: Bindī is transliterated by:\n\n      a) ṅ before gutturals,\n      b) ñ before palatals,\n      c) ṇ before cerebrals,\n      d) n before dentals, and\n      e) m before labials."
+
+    note "      Exception: Ṭippī is transliterated by:\n\n      a) ṅ before gutturals,\n      b) ñ before palatals,\n      c) ṇ before cerebrals,\n      d) n before dentals, and\n      e) m before labials."
+
+    note "      Exception: When adhik implies the combination of a non-aspirated and an aspirated\n      consonant, the combination is transliterated as a non-aspirated, followed by an aspirated\n      consonant."
+  }
+}
+
+tests {
+   "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ" ->  "pañjaāba 'ca wadha raihaā khaudakaushaīāṃ daā raujhaāna"
+   "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ" ->  "lakkha taoṃ paāra paujjaā saragarama kaesaāṃ daā aṅkaṛaā, daillaī 'ca dao lakkha taoṃ paāra inaphaaikaṭaiḍa"
+   "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ" ->  "paraiwaāraka samassaiāwaāṃ atae waiāha waī haai haora ahaima kaārana"
+   "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ" ->  "maradaāṃ 'ca aurataāṃ naālaoṃ waddha haai khaudakaushaī daā raujhaāna"
+   "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ" ->  "raāshaṭaraī paddhara 'tae pañjaāba daī sathaitaī kaāfaī saūbaiāṃ taoṃ baihatara"
+   "ਚੀਨੀ ਸੈਨਾ ਨੇ ਲਾਪਤਾ ਅਰੁਣਾਚਲ ਦੇ 5 ਨੌਜਵਾਨਾਂ ਬਾਰੇ ਦੱਸਿਆ" ->  "caīnaī saainaā nae laāpataā arauṇaācala dae 5 naaujawaānaāṃ baārae dassaiā"
+   "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ" ->  "saākharataā dae maāmalae 'ca daesha 'ca 7waeṃ nam̆̐bara 'tae pañjaāba"
+   "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ" ->  "daillaī kamaeṭaī dae maaiṃbara shaṇṭaī nae akaālaī dala taoṃ daittaā asataīfaā"
+   "੧੦੨ ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ" ->  "102 haora kaoraonaā paāzaīṭaiwa maraīzaāṃ daī paushaṭaī, ika daī maauta"
+   "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ" ->  "saṛaka haādasae daauraāna ika daī maauta"
+}
+
+stage main {
+
+  # RULES
+  # note[4]
+  sub {
+    from "\u0A02"
+    to "ṅ"
+    after any("ਕਖਖ਼ਗਗ਼ਘਙ")
+  }
+  sub {
+    from "\u0A02"
+    to "ñ"
+    after any("ਚਛਜਜ਼ਝਞ")
+  }
+  sub {
+    from "\u0A02"
+    to "ṇ"
+    after any("ਟਠਡਢਣ")
+  }
+  sub {
+    from "\u0A02"
+    to "n"
+    after any("ਤਥਦਧਨ")
+  }
+
+  # note[5]
+  sub {
+    from "\u0A70"
+    to "ṅ"
+    after any("ਕਖਖ਼ਗਗ਼ਘਙ")
+  }
+  sub {
+    from "\u0A70"
+    to "ñ"
+    after any("ਚਛਜਜ਼ਝਞ")
+  }
+  sub {
+    from "\u0A70"
+    to "ṇ"
+    after any("ਟਠਡਢਣ")
+  }
+  sub {
+    from "\u0A70"
+    to "n"
+    after any("ਤਥਦਧਨ")
+  }
+
+
+  # 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"
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "ਕ" "ka"
+    sub "ਖ" "kha"
+    sub "ਖ਼" "kha"
+    sub "ਗ" "ga"
+    sub "ਗ਼" "gha"
+    sub "ਘ" "gha"
+    sub "ਙ" "ṅa"
+
+    # Palatals
+    sub "ਚ" "ca"
+    sub "ਛ" "cha"
+    sub "ਜ਼" "za"
+    sub "ਜ" "ja"
+    sub "ਝ" "jha"
+    sub "ਞ" "ña"
+
+    # Cerebrals
+    sub "ਟ" "ṭa"
+    sub "ਠ" "ṭha"
+    sub "ਡ" "ḍa"
+    sub "ਢ" "ḍha"
+    sub "ਣ" "ṇa"
+
+    # Dentals
+    sub "ਤ" "ta"
+    sub "ਥ" "tha"
+    sub "ਦ" "da"
+    sub "ਧ" "dha"
+    sub "ਨ" "na"
+
+    # Labials
+    sub "ਪ" "pa"
+    sub "ਫ" "pha"
+    sub "ਫ਼" "fa"
+    sub "ਬ" "ba"
+    sub "ਭ" "bha"
+    sub "ਮ" "ma"
+
+    # Semivowels
+    sub "ਯ" "ya"
+    sub "ਰ" "ra"
+    sub "ਲ" "la"
+    sub "ਲੵ" "ḷa"
+    sub "ਲ਼" "ḷa"
+    sub "ਵ" "wa"
+    sub "ੜ" "ṛa"
+
+    # Sibilants
+    sub "ਸ" "sa"
+    sub "ਸ਼" "sha"
+
+    # Aspirate
+    sub "ਹ" "ha"
+
+    # Bindī (see Note 4)
+    sub "ਂ" "ṃ"
+
+    # Ṭippī (see Note 5)
+    sub "ੰ" "m̆̐"
+
+    # Medials # Needed for connecting constants
+    sub "ਾ" "ā"
+    sub "ਿ" "i"
+    sub "ੀ" "ī"
+    sub "ੁ" "u"
+    sub "ੂ" "ū"
+    sub "ੇ" "e"
+    sub "ੈ" "ai"
+    sub "ੋ" "o"
+    sub "ੌ" "au"
+
+    # For adhik character[Note 6]
+
+    # Gutturals
+    sub "ੱਕ" "kka"
+    sub "ੱਖ" "kkha"
+    sub "ੱਖ਼" "kkha"
+    sub "ੱਗ" "gga"
+    sub "ੱਗ਼" "ggha"
+    sub "ੱਘ" "ggha"
+    sub "ੱਙ" "ṅṅa"
+
+    # Palatals
+    sub "ੱਚ" "cca"
+    sub "ੱਛ" "ccha"
+    sub "ੱਜ" "jja"
+    sub "ੱਜ਼" "zza"
+    sub "ੱਝ" "jjha"
+    sub "ੱਞ" "ñña"
+
+    # Cerebrals
+    sub "ੱਟ" "ṭṭa"
+    sub "ੱਠ" "ṭṭha"
+    sub "ੱਡ" "ḍḍa"
+    sub "ੱਢ" "ḍḍha"
+    sub "ੱਣ" "ṇṇa"
+
+    # Dentals
+    sub "ੱਤ" "tta"
+    sub "ੱਥ" "ttha"
+    sub "ੱਦ" "dda"
+    sub "ੱਧ" "ddha"
+    sub "ੱਨ" "nna"
+
+    # Labials
+    sub "ੱਪ" "ppa"
+    sub "ੱਫ" "ppha"
+    sub "ੱਫ਼" "ffa"
+    sub "ੱਬ" "bba"
+    sub "ੱਭ" "bbha"
+    sub "ੱਮ" "mma"
+
+    # Semivowels
+    sub "ੱਯ" "yya"
+    sub "ੱਰ" "rra"
+    sub "ੱਲ" "lla"
+    sub "ੱਲੵ" "ḷḷa"
+    sub "ੱਵ" "wwa"
+    sub "ੱੜ" "ṛṛa"
+
+    # Sibilants
+    sub "ੱਸ" "ssa"
+    sub "ੱਸ਼" "ssha"
+
+    # Aspirate
+    sub "ੱਹ" "hha"
+
+
+    # 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
+}
+}