interscript-maps 2.0.5

data/maps/iso-mar-Deva-Latn-15919-2001.imp

@@ -0,0 +1,68 @@
+metadata {
+  authority_id: iso
+  id: 15919-2001
+  language: iso-639-2:mar
+  source_script: Deva
+  destination_script: Latn
+  name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+  url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+  creation_date: 2001
+  adoption_date: 2001
+  description: |
+    Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+    maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+    Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+    equipment that they are using, cannot read or write the text
+
+    This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+    independent of the period in which it is or was used.
+
+  notes:
+
+    - All transliterations made using this International Standard shall be case-insensitive.
+    - Inherent a with a consonant shall always be transliterated.
+    - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+    - candrabindu shall be transliterated as m̐
+    - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+      with a semivowel, it shall be placed before the semivowel.
+    - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+      Indic punctuation is outside the scope of this International Standard.
+    - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+      independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+      shall be attached to the second vowel.
+    - |
+      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+      follows.
+       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+       -  Vowel hiatus, not digraph transliteration of diphthongs; as in Sanskrit pra:uga (not prauga), “yoke”;
+
+    - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+      script, where the second character has a transliteration in this International Standard, then the first character shall
+      be transliterated in the same way as the second character.
+    - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+      the digraphs ai, au, both Latin vowels should be underscored.
+      Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+      consonant, the transliteration should show word division by a space; but when phonological processes result in two
+      words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+      of the language in question.
+}
+
+tests {
+  test "ठाणे - जिल्ह्यात बुधवारी एक हजार रुग्णांची वाढ, तर जणांच्या मृत्यूची नोंद", "ṭhaāṇae - jailahayaāta baudhavaāraī eka hajaāra raugaṇaāṁcaī vaāḍha, tara jaṇaāṁcayaā maṛtayaūcaī naoṁda"
+  test "एकता कपूर पुन्हा अडकली वादात, वेबसीरिजमधल्या 'त्या' सीनमुळे जमावाची घरावर दगडफेक", "ekataā kapaūra paunahaā aḍakalaī vaādaāta, vaebasaīraijamadhalayaā 'tayaā' saīnamauḷae jamaāvaācaī gharaāvara dagaḍaphaeka"
+  test "जाणून घ्या, बीएमसीच्या अधिकाऱ्यांनी कंगना राणौतच्या ऑफिसमधले नक्की काय- काय तोडलं", "jaāṇaūna ghayaā, baīemasaīcayaā adhaikaāऱyaāṁnaī kaṁganaā raāṇaautacayaā ôphaisamadhalae nakakaī kaāya- kaāya taoḍalaṁ"
+  test "कंगना मुंबईत दाखल होण्यापूर्वी 'मातोश्री'वरून फर्मान सुटले; प्रवक्त्यांना सक्त आदेश", "kaṁganaā mauṁbaīta daākhala haoṇayaāpaūravaī 'maātaośaraī'varaūna pharamaāna sauṭalae; paravakatayaāṁnaā sakata ādaeśa"
+  test "मराठा आरक्षणास तात्पुरती स्थगिती; सर्वोच्च न्यायालयाचा निर्णय", "maraāṭhaā ārakaṣaṇaāsa taātapaurataī sathagaitaī; saravaocaca nayaāyaālayaācaā nairaṇaya"
+  test "भारताच्या तिन्ही लशींचा पहिला टप्पा यशस्वी, वाचा कधी येणार बाजारात", "bhaārataācayaā tainahaī laśaīṁcaā pahailaā ṭapapaā yaśasavaī, vaācaā kadhaī yaeṇaāra baājaāraāta"
+  test "रुग्णवाढीमुळे खाटांची चणचण", "raugaṇavaāḍhaīmauḷae khaāṭaāṁcaī caṇacaṇa"
+  test "पीएम स्वनिधी कर्ज योजनेला मुंबईतून अल्प प्रतिसाद", "paīema savanaidhaī karaja yaojanaelaā mauṁbaītaūna alapa parataisaāda"
+  test "सांताक्रूझ-चेंबूर लिंक रोडवरील उन्नत मार्गाला स्थगिती", "saāṁtaākaraūjha-caeṁbaūra laiṁka raoḍavaraīla unanata maāragaālaā sathagaitaī"
+  test "संपादक अर्णब गोस्वामी यांच्याविरूद्ध खडक पोलिस ठाण्यात तक्रार", "saṁpaādaka araṇaba gaosavaāmaī yaāṁcayaāvairaūdadha khaḍaka paolaisa ṭhaāṇayaāta takaraāra"
+}
+
+dependency "iso-san-Deva-Latn-15919-2001", as: devalatn
+
+stage {
+  run map.devalatn.stage.main
+}

data/maps/iso-nep-Deva-Latn-15919-2001.imp

@@ -0,0 +1,75 @@
+metadata {
+  authority_id: iso
+  id: 15919-2001
+  language: iso-639-2:nep
+  source_script: Deva
+  destination_script: Latn
+  name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+  url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+  creation_date: 2001
+  adoption_date: 2001
+  description: |
+    Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+    maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+    Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+    equipment that they are using, cannot read or write the text
+
+    This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+    independent of the period in which it is or was used.
+
+  notes:
+
+    - All transliterations made using this International Standard shall be case-insensitive.
+    - Inherent a with a consonant shall always be transliterated.
+    - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+    - candrabindu shall be transliterated as m̐
+    - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+      with a semivowel, it shall be placed before the semivowel.
+    - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+      Indic punctuation is outside the scope of this International Standard.
+    - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+      independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+      shall be attached to the second vowel.
+    - |
+      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+      follows.
+       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+       -  Vowel hiatus, not digraph transliteration of diphthongs; as in Sanskrit pra:uga (not prauga), “yoke”;
+       -  Absence of aspiration, as in the Nepali plural form vid:harū (not vidharū )
+
+    - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+      script, where the second character has a transliteration in this International Standard, then the first character shall
+      be transliterated in the same way as the second character.
+    - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+      the digraphs ai, au, both Latin vowels should be underscored.
+      Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+      consonant, the transliteration should show word division by a space; but when phonological processes result in two
+      words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+      of the language in question.
+}
+
+tests {
+  test "लेखन", "laekhana"
+  test "मुद्रा", "maudaraā"
+  test "प्रशंसा", "paraśaṁsaā"
+  test "अंक", "aṁka"
+  test "नेकपाले स्थगित स्थायी कमिटीको बैठक भदौ गते बोलाउने भएको", "naekapaālae sathagaita sathaāyaī kamaiṭaīkao baaiṭhaka bhadaau gatae baolaāunae bhaekao"
+  test "न घर रह्यो, न परिवार", "na ghara rahayao, na paraivaāra"
+  test "ढोरपाटनमा भुजीखोला बाढीपहिरोले अभिभावक गुमाएका बालबालिकाको बिचल्ली", "ḍhaorapaāṭanamaā bhaujaīkhaolaā baāḍhaīpahairaolae abhaibhaāvaka gaumaāekaā baālabaālaikaākao baicalalaī"
+  test "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो", "sausamaitaākaā kaākaā haemabahaādaura ra kaākaīlaāī panai pahairaolae bagaāyao"
+  test "संविधान जारी भएसँगै सार्वजनिक प्रशासनमा नयाँ उत्साह आउने अपेक्षा थियो", "saṁvaidhaāna jaāraī bhaesam̐gaai saāravajanaika paraśaāsanamaā nayaām̐ utasaāha āunae apaekaṣaā thaiyao"
+  test "देशमा कोरोना संक्रमित र मृतकको संख्या हरेक दिन बढ्दो छ", "daeśamaā kaoraonaā saṁkaramaita ra maṛtakakao saṁkhayaā haraeka daina baḍhadao cha"
+  test "गाउँपालिकाका अध्यक्ष टिका गुरुङका अनुसार विष्णुदासलाई राजुले सुत्नका लागि बेलुका साथी लगेका थिए", "gaāum̐paālaikaākaā adhayakaṣa ṭaikaā gaurauṅakaā anausaāra vaiṣaṇaudaāsalaāī raājaulae sautanakaā laāgai baelaukaā saāthaī lagaekaā thaie"
+  test "यो आयोजना गाउँपालिकाको केन्द्र तेल्लोकमा पर्छ", "yao āyaojanaā gaāum̐paālaikaākao kaenadara taelalaokamaā paracha"
+  test "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो", "sausamaitaākaā kaākaā haemabahaādaura ra kaākaīlaāī panai pahairaolae bagaāyao"
+  test "चैत पहिलो साता घर आएका उनी लकडाउन भएपछि यतै रोकिए", "caaita pahailao saātaā ghara āekaā unaī lakaḍaāuna bhaepachai yataai raokaie"
+  test "काम गर्न जानेको हकमा रोजगारदाता कम्पनीको पत्रसँगै वडा र जिल्ला प्रशासनको सिफारिस अनिवार्य गरिएको छ", "kaāma garana jaānaekao hakamaā raojagaāradaātaā kamapanaīkao patarasam̐gaai vaḍaā ra jailalaā paraśaāsanakao saiphaāraisa anaivaāraya garaiekao cha"
+  test "दुःख", "dauḥkha"
+}
+
+dependency "iso-san-Deva-Latn-15919-2001", as: devalatn
+
+stage {
+  run map.devalatn.stage.main
+}

data/maps/iso-ori-Orya-Latn-15919-2001.imp

@@ -0,0 +1,188 @@
+metadata {
+  authority_id: iso
+  id: 15919-2001
+  language: iso-639-2:ori
+  source_script: Deva
+  destination_script: Latn
+  name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+  url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+  creation_date: 2001
+  adoption_date: 2001
+  description: |
+    Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+    maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+    Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+    equipment that they are using, cannot read or write the text
+
+    This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+    independent of the period in which it is or was used.
+
+  notes:
+
+    - All transliterations made using this International Standard shall be case-insensitive.
+    - Inherent a with a consonant shall always be transliterated.
+    - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+    - candrabindu shall be transliterated as m̐
+    - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+      with a semivowel, it shall be placed before the semivowel.
+    - Secondary ya/ẏa in Oriya scripts shall be transliterated as ya, except that it shall be
+      transliterated as ẏa after ẏ .
+    - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+      Indic punctuation is outside the scope of this International Standard.
+    - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+      independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+      shall be attached to the second vowel.
+    - |
+      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+      follows.
+       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+       - Unexpected use of secondary ba, as in Oriya o:ba (not oba), English “wa”.
+    - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+      script, where the second character has a transliteration in this International Standard, then the first character shall
+      be transliterated in the same way as the second character.
+    - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+      the digraphs ai, au, both Latin vowels should be underscored.
+      Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+      consonant, the transliteration should show word division by a space; but when phonological processes result in two
+      words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+      of the language in question.
+}
+
+tests {
+  test "ସାମ୍ପ୍ରତିକ ବିଶ୍ବ ସ୍ଥିତାବସ୍ଥାକୁ ଚାଲେଞ୍ଜ୍‌ କରୁଥିବା ଦୁଇ ମୁଖ୍ୟ ପ୍ରତିଦ୍ବନ୍ଦ୍ବୀ ହେଉଛନ୍ତି ଚୀନ୍‌ ଓ ରୁଷ୍: ଇଂଲଣ୍ଡ୍‌ ଗୁଇନ୍ଦା ଅଧିକାରୀ", "saāmaparataika baiśaba sathaitaābasathaākau caālaeñaja karauthaibaā daui maukhaẏa parataidabanadabaī haeuchanatai caīna o rauṣa: iṁlaṇaḍa gauinadaā adhaikaāraī"
+  test "ଏଣିକି ଏହି ଗାଡ଼ି ଚଳାଇଲେ ପୁଲିସ କାଟି ପାରିବ ନାହିଁ ଫାଇନ୍", "eṇaikai ehai gaāṛai caḷaāilae paulaisa kaāṭai paāraiba naāhaim̐ phaāina"
+  test "ପିସି କାରବାର ଘଟଣା, ନିଲମ୍ବନ ହେଲେ ପଞ୍ଚାୟତ ଅଧିକାରୀ", "paisai kaārabaāra ghaṭaṇaā, nailamabana haelae pañacaāẏata adhaikaāraī"
+  test "ବରିଷ୍ଠ ଓଡ଼ିଆ ଚଳଚ୍ଚିତ୍ର ଅଭିନେତା ଅଜିତ ଦାସଙ୍କ", "baraiṣaṭha oḍaiā caḷacacaitara abhainaetaā ajaita daāsaṅaka"
+  test "ସଞ୍ଚୟ କରିବାରେ କେଉଁ ରାଶି ଅଧିକ ସତର୍କ ?", "sañacaẏa karaibaārae kaeum̐ raāśai adhaika sataraka ?"
+  test "କର୍କଟ ରାଶିର ଅଧିକାରୀ ନିଜ ଜ୍ଞାତିପରିଜନଙ୍କ ପାଇଁ ଟଙ୍କା ଖର୍ଚ୍ଚ କରିବାକୁ ପସନ୍ଦ କରିଥାନ୍ତି।", "karakaṭa raāśaira adhaikaāraī naija jañaātaiparaijanaṅaka paāim̐ ṭaṅakaā kharacaca karaibaākau pasanada karaithaānatai."
+  test "ବୃଷ ରାଶିର ବ୍ୟକ୍ତିମାନେ ସ୍ବଭାବରେ କଞ୍ଜୁସ୍ କିମ୍ବା କୃପଣ ନୁହନ୍ତି", "baṛṣa raāśaira baẏakataimaānae sababhaābarae kañajausa kaimabaā kaṛpaṇa nauhanatai"
+  test "ନବନିଯୁକ୍ତ ଓଡିଶା କଂଗ୍ରେସ ପ୍ରଭାରୀ ଏ.ଚେଲ୍ଲା କୁମାରଙ୍କୁ କରୋନା", "nabanaiyaukata oḍaiśaā kaṁgaraesa parabhaāraī e.caelalaā kaumaāraṅakau karaonaā"
+  test "ଦିଲ୍ଲୀ: ଦିନ ଦ୍ବିପହରରେ ଗାଡ଼ି ଉପରକୁ ଦୁର୍ବୃତ୍ତ ଚଳାଇଲେ ୮ ରାଉଣ୍ଡ ଗୁଳି: ଚାଳକଙ୍କ ମୃତ୍ୟୁ", "dailalaī: daina dabaipahararae gaāṛai uparakau daurabaṛtata caḷaāilae ୮ raāuṇaḍa gauḷai: caāḷakaṅaka maṛtaẏau"
+  test "ବୟସରେ ଆର ପାରିକୁ ଚାଲିଗଲେ କଣ୍ଠଶିଳ୍ପୀ ଅନୁରାଧା ପୋଡୱାଲଙ୍କ ପୁଅ ଆଦିତ୍ୟ", "baẏasarae āra paāraikau caālaigalae kaṇaṭhaśaiḷapaī anauraādhaā paeāḍawaālaṅaka paua ādaitaẏa"
+}
+
+stage {
+
+  # 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", "ḷ"
+    sub "ୡ", "ḹ"
+    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 "ଡ଼", "ṛa"
+    sub "ଢ", "ḍha"
+    sub "ଢ଼", "ṛha"
+    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"
+    sub "ଵ", "va"
+
+    # Sibilants
+    sub "ଶ", "śa"
+    sub "ଷ", "ṣa"
+    sub "ସ", "sa"
+
+    sub "ୱ", "wa"
+
+
+    # Aspirate
+    sub "ହ", "ha"
+
+    # Chandrabindu
+    sub "ଁ", "m̐"
+
+    # Bisarga
+    sub "ଃ", "ḥ"
+
+    # Anusvāra
+    sub "ଂ", "ṁ"
+
+    # Medials # Needed for connecting constants
+
+    sub "ା", "ā"
+    sub "ି", "i"
+    sub "ୀ", "ī"
+    sub "ୁ", "u"
+    sub "ୂ", "ū"
+    sub "\u0B43", "ṛ"
+    sub "\u0B44", "ṝ"
+    sub "\u0B62", "ḷ"
+    sub "\u0B63", "ḹ"
+    sub "େ", "e"
+    sub "ୈ", "ai"
+    sub "ୋ", "o"
+    sub "ୌ", "au"
+
+    # Abagraha
+    sub "ଽ", ":’"
+
+    sub "्", ""
+    sub "୍", ""
+    sub "़", ""
+    sub "଼", ""
+    sub "।", "."
+    sub "‍", "" # Used for joining
+    sub "‌", "" # Used for non joining
+
+    # for semivowel rule no. 5
+
+    sub "ଯଁ", "m̐ya"
+    sub "ୟଁ", "m̐ẏa"
+    sub "ରଁ", "m̐ra"
+    sub "ଲଁ", "m̐la"
+    sub "ଳଁ", "m̐ḷa"
+    sub "ଵଁ", "m̐va"
+  }
+
+  compose
+}

data/maps/iso-pan-Guru-Latn-15919-2001.imp

@@ -0,0 +1,217 @@
+metadata {
+  authority_id: iso
+  id: 15919-2001
+  language: iso-639-2:pan
+  source_script: Guru
+  destination_script: Latn
+  name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+  url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+  creation_date: 2001
+  adoption_date: 2001
+  description: |
+    Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+    maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+    Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+    equipment that they are using, cannot read or write the text
+
+    This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+    independent of the period in which it is or was used.
+
+  notes:
+
+    - All transliterations made using this International Standard shall be case-insensitive.
+    - Inherent a with a consonant shall always be transliterated.
+    - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+    - candrabindu shall be transliterated as m̐
+    - Bindi shall be transliterated as ṃ and Tippi as ṁ .
+    - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+      with a semivowel, it shall be placed before the semivowel.
+    - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+      Indic punctuation is outside the scope of this International Standard.
+    - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+      independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+      shall be attached to the second vowel.
+    - |
+      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+      follows.
+       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+       - Removal of ambiguity in the limited character set option. Tamil perii:i:iya, “really big”, separating the vowels.
+       - Gurmukhi Adhik before a vowel, as in bac: ā (not bacā without Adhik).
+       - Gurmukhi Bindi or Tippi written before the vowel ī (instead of after the vowel) in old orthography, transliterated
+      as ī:ṃ or ī:ṁ , respectively.
+       - Gurmukhi hala making a conjunct h in old orthography, as in tum:ha formed with hala (not tumha formed with the usual subscript h).
+    - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+      script, where the second character has a transliteration in this International Standard, then the first character shall
+      be transliterated in the same way as the second character.
+    - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+      the digraphs ai, au, both Latin vowels should be underscored.
+      Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+      consonant, the transliteration should show word division by a space; but when phonological processes result in two
+      words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+      of the language in question.
+}
+
+tests {
+  test "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ", "paṁjaāba 'ca vadha raihaā ḵẖaudakauśaīāṃ daā raujhaāna"
+  test "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ", "lakha taoṃ paāra paujaā saragarama kaesaāṃ daā aṁkaṛaā, dailaī 'ca dao lakha taoṃ paāra inaphaaikaṭaiḍa"
+  test "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ", "paraivaāraka samasaiāvaāṃ atae vaiāha vaī haai haora ahaima kaārana"
+  test "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ", "maradaāṃ 'ca aurataāṃ naālaoṃ vadha haai ḵẖaudakauśaī daā raujhaāna"
+  test "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ", "raāśaṭaraī padhara 'tae paṁjaāba daī sathaitaī kaāfaī saūbaiāṃ taoṃ baihatara"
+  test "ਚੀਨੀ ਸੈਨਾ ਨੇ ਲਾਪਤਾ ਅਰੁਣਾਚਲ ਦੇ 5 ਨੌਜਵਾਨਾਂ ਬਾਰੇ ਦੱਸਿਆ", "caīnaī saainaā nae laāpataā arauṇaācala dae 5 naaujavaānaāṃ baārae dasaiā"
+  test "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ", "saākharataā dae maāmalae 'ca daeśa 'ca 7vaeṃ naṁbara 'tae paṁjaāba"
+  test "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ", "dailaī kamaeṭaī dae maaiṃbara śaṁṭaī nae akaālaī dala taoṃ daitaā asataīfaā"
+  test "੧੦੨ ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ", "102 haora kaoraonaā paāzaīṭaiva maraīzaāṃ daī pauśaṭaī, ika daī maauta"
+  test "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ", "saṛaka haādasae daauraāna ika daī maauta"
+  test "ਅਸੀਂ ਲੁੱਕ ਛੁੱਪ ਕ਼ ਆਪਣੀ ਜਾਨ", "asaīṃ lauka chaupa qa āpaṇaī jaāna"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+
+    # Vowels
+
+    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"
+
+    # Consonants
+    # Gutturals
+    sub "ਕ", "ka"
+    sub "ਖ", "kha"
+    sub "ਗ", "ga"
+    sub "ਘ", "gha"
+    sub "ਙ", "ṅa"
+
+    # Palatals
+    sub "ਚ", "ca"
+    sub "ਛ", "cha"
+    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 "ਬ", "ba"
+    sub "ਭ", "bha"
+    sub "ਮ", "ma"
+
+    # Semivowels
+    sub "ਯ", "ya"
+    sub "ਰ", "ra"
+    sub "ਲ", "la"
+    sub "ਲ਼", "ḷa"
+    sub "ਵ", "va"
+    sub "ੜ", "ṛa"
+
+    # Sibilants
+    sub "ਸ", "sa"
+
+    # Aspirate
+    sub "ਹ", "ha"
+
+    # Bindī
+    sub "ਂ", "ṃ"
+
+    # Ṭippī
+    sub "ੰ", "ṁ"
+
+    # Bisarga
+    sub "ਃ", "ḥ"
+
+    # candrabindu
+    sub "\u0A01", "m̐"
+
+
+    # Medials # Needed for connecting constants
+    sub "ਾ", "ā"
+    sub "ਿ", "i"
+    sub "ੀ", "ī"
+    sub "ੁ", "u"
+    sub "ੂ", "ū"
+    sub "ੇ", "e"
+    sub "ੈ", "ai"
+    sub "ੋ", "o"
+    sub "ੌ", "au"
+    sub "ੱ", ""
+
+    # For adhik before a vowel rule 9 exception
+
+    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"
+
+
+    # rule 9 exception for bindi and tippi
+
+    sub "ਂਈ", "ī:ṃ"
+    sub "ੰਈ", "ī:ṁ"
+
+
+    # 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"
+
+
+    # Perso-Arabic Characters
+
+    sub "ਖ਼", "ḵẖa"
+    sub "ਕ਼", "qa"
+    sub "ਗ਼", "ġa"
+    sub "ਫ਼", "fa"
+    sub "ਸ਼", "śa"
+    sub "ਜ਼", "za"
+  }
+
+  compose
+}