interscript 0.1.2 → 0.1.7

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

@@ -0,0 +1,75 @@
+---
+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:
+  - source: "ठाणे - जिल्ह्यात बुधवारी एक हजार रुग्णांची वाढ, तर जणांच्या मृत्यूची नोंद"
+    expected: "ṭhaāṇae - jailahayaāta baudhavaāraī eka hajaāra raugaṇaāṁcaī vaāḍha, tara jaṇaāṁcayaā maṛtayaūcaī naoṁda"
+  - source: "एकता कपूर पुन्हा अडकली वादात, वेबसीरिजमधल्या 'त्या' सीनमुळे जमावाची घरावर दगडफेक"
+    expected: "ekataā kapaūra paunahaā aḍakalaī vaādaāta, vaebasaīraijamadhalayaā 'tayaā' saīnamauḷae jamaāvaācaī gharaāvara dagaḍaphaeka"
+  - source: "जाणून घ्या, बीएमसीच्या अधिकाऱ्यांनी कंगना राणौतच्या ऑफिसमधले नक्की काय- काय तोडलं"
+    expected: "jaāṇaūna ghayaā, baīemasaīcayaā adhaikaāऱyaāṁnaī kaṁganaā raāṇaautacayaā ôphaisamadhalae nakakaī kaāya- kaāya taoḍalaṁ"
+  - source: "कंगना मुंबईत दाखल होण्यापूर्वी 'मातोश्री'वरून फर्मान सुटले; प्रवक्त्यांना सक्त आदेश"
+    expected: "kaṁganaā mauṁbaīta daākhala haoṇayaāpaūravaī 'maātaośaraī'varaūna pharamaāna sauṭalae; paravakatayaāṁnaā sakata ādaeśa"
+  - source: "मराठा आरक्षणास तात्पुरती स्थगिती; सर्वोच्च न्यायालयाचा निर्णय"
+    expected: "maraāṭhaā ārakaṣaṇaāsa taātapaurataī sathagaitaī; saravaocaca nayaāyaālayaācaā nairaṇaya"
+  - source: "भारताच्या तिन्ही लशींचा पहिला टप्पा यशस्वी, वाचा कधी येणार बाजारात"
+    expected: "bhaārataācayaā tainahaī laśaīṁcaā pahailaā ṭapapaā yaśasavaī, vaācaā kadhaī yaeṇaāra baājaāraāta"
+  - source: "रुग्णवाढीमुळे खाटांची चणचण"
+    expected: "raugaṇavaāḍhaīmauḷae khaāṭaāṁcaī caṇacaṇa"
+  - source: "पीएम स्वनिधी कर्ज योजनेला मुंबईतून अल्प प्रतिसाद"
+    expected: "paīema savanaidhaī karaja yaojanaelaā mauṁbaītaūna alapa parataisaāda"
+  - source: "सांताक्रूझ-चेंबूर लिंक रोडवरील उन्नत मार्गाला स्थगिती"
+    expected: "saāṁtaākaraūjha-caeṁbaūra laiṁka raoḍavaraīla unanata maāragaālaā sathagaitaī"
+  - source: "संपादक अर्णब गोस्वामी यांच्याविरूद्ध खडक पोलिस ठाण्यात तक्रार"
+    expected: "saṁpaādaka araṇaba gaosavaāmaī yaāṁcayaāvairaūdadha khaḍaka paolaisa ṭhaāṇayaāta takaraāra"
+
+map:
+
+  inherit: iso-san-Deva-Latn-15919-2001

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

@@ -0,0 +1,87 @@
+---
+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:
+  - source: "लेखन"
+    expected: "laekhana"
+  - source: "मुद्रा"
+    expected: "maudaraā"
+  - source: "प्रशंसा"
+    expected: "paraśaṁsaā"
+  - source: "अंक"
+    expected: "aṁka"
+  - source: "नेकपाले स्थगित स्थायी कमिटीको बैठक भदौ गते बोलाउने भएको"
+    expected: "naekapaālae sathagaita sathaāyaī kamaiṭaīkao baaiṭhaka bhadaau gatae baolaāunae bhaekao"
+  - source: "न घर रह्यो, न परिवार"
+    expected: "na ghara rahayao, na paraivaāra"
+  - source: "ढोरपाटनमा भुजीखोला बाढीपहिरोले अभिभावक गुमाएका बालबालिकाको बिचल्ली"
+    expected: "ḍhaorapaāṭanamaā bhaujaīkhaolaā baāḍhaīpahairaolae abhaibhaāvaka gaumaāekaā baālabaālaikaākao baicalalaī"
+  - source: "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो"
+    expected: "sausamaitaākaā kaākaā haemabahaādaura ra kaākaīlaāī panai pahairaolae bagaāyao"
+  - source: "संविधान जारी भएसँगै सार्वजनिक प्रशासनमा नयाँ उत्साह आउने अपेक्षा थियो"
+    expected: "saṁvaidhaāna jaāraī bhaesam̐gaai saāravajanaika paraśaāsanamaā nayaām̐ utasaāha āunae apaekaṣaā thaiyao"
+  - source: "देशमा कोरोना संक्रमित र मृतकको संख्या हरेक दिन बढ्दो छ"
+    expected: "daeśamaā kaoraonaā saṁkaramaita ra maṛtakakao saṁkhayaā haraeka daina baḍhadao cha"
+  - source: "गाउँपालिकाका अध्यक्ष टिका गुरुङका अनुसार विष्णुदासलाई राजुले सुत्नका लागि बेलुका साथी लगेका थिए"
+    expected: "gaāum̐paālaikaākaā adhayakaṣa ṭaikaā gaurauṅakaā anausaāra vaiṣaṇaudaāsalaāī raājaulae sautanakaā laāgai baelaukaā saāthaī lagaekaā thaie"
+  - source: "यो आयोजना गाउँपालिकाको केन्द्र तेल्लोकमा पर्छ"
+    expected: "yao āyaojanaā gaāum̐paālaikaākao kaenadara taelalaokamaā paracha"
+  - source: "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो"
+    expected: "sausamaitaākaā kaākaā haemabahaādaura ra kaākaīlaāī panai pahairaolae bagaāyao"
+  - source: "चैत पहिलो साता घर आएका उनी लकडाउन भएपछि यतै रोकिए"
+    expected: "caaita pahailao saātaā ghara āekaā unaī lakaḍaāuna bhaepachai yataai raokaie"
+  - source: "काम गर्न जानेको हकमा रोजगारदाता कम्पनीको पत्रसँगै वडा र जिल्ला प्रशासनको सिफारिस अनिवार्य गरिएको छ"
+    expected: "kaāma garana jaānaekao hakamaā raojagaāradaātaā kamapanaīkao patarasam̐gaai vaḍaā ra jailalaā paraśaāsanakao saiphaāraisa anaivaāraya garaiekao cha"
+  - source: "दुःख"
+    expected: "dauḥkha"
+map:
+
+  inherit: iso-san-Deva-Latn-15919-2001

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

@@ -0,0 +1,193 @@
+---
+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:
+  - source: "ସାମ୍ପ୍ରତିକ ବିଶ୍ବ ସ୍ଥିତାବସ୍ଥାକୁ ଚାଲେଞ୍ଜ୍‌ କରୁଥିବା ଦୁଇ ମୁଖ୍ୟ ପ୍ରତିଦ୍ବନ୍ଦ୍ବୀ ହେଉଛନ୍ତି ଚୀନ୍‌ ଓ ରୁଷ୍: ଇଂଲଣ୍ଡ୍‌ ଗୁଇନ୍ଦା ଅଧିକାରୀ"
+    expected: "saāmaparataika baiśaba sathaitaābasathaākau caālaeñaja karauthaibaā daui maukhaẏa parataidabanadabaī haeuchanatai caīna o rauṣa: iṁlaṇaḍa gauinadaā adhaikaāraī"
+  - source: "ଏଣିକି ଏହି ଗାଡ଼ି ଚଳାଇଲେ ପୁଲିସ କାଟି ପାରିବ ନାହିଁ ଫାଇନ୍"
+    expected: "eṇaikai ehai gaāṛai caḷaāilae paulaisa kaāṭai paāraiba naāhaim̐ phaāina"
+  - source: "ପିସି କାରବାର ଘଟଣା, ନିଲମ୍ବନ ହେଲେ ପଞ୍ଚାୟତ ଅଧିକାରୀ"
+    expected: "paisai kaārabaāra ghaṭaṇaā, nailamabana haelae pañacaāẏata adhaikaāraī"
+  - source: "ବରିଷ୍ଠ ଓଡ଼ିଆ ଚଳଚ୍ଚିତ୍ର ଅଭିନେତା ଅଜିତ ଦାସଙ୍କ"
+    expected: "baraiṣaṭha oḍaiā caḷacacaitara abhainaetaā ajaita daāsaṅaka"
+  - source: "ସଞ୍ଚୟ କରିବାରେ କେଉଁ ରାଶି ଅଧିକ ସତର୍କ ?"
+    expected: "sañacaẏa karaibaārae kaeum̐ raāśai adhaika sataraka ?"
+  - source: "କର୍କଟ ରାଶିର ଅଧିକାରୀ ନିଜ ଜ୍ଞାତିପରିଜନଙ୍କ ପାଇଁ ଟଙ୍କା ଖର୍ଚ୍ଚ କରିବାକୁ ପସନ୍ଦ କରିଥାନ୍ତି।"
+    expected: "karakaṭa raāśaira adhaikaāraī naija jañaātaiparaijanaṅaka paāim̐ ṭaṅakaā kharacaca karaibaākau pasanada karaithaānatai."
+  - source: "ବୃଷ ରାଶିର ବ୍ୟକ୍ତିମାନେ ସ୍ବଭାବରେ କଞ୍ଜୁସ୍ କିମ୍ବା କୃପଣ ନୁହନ୍ତି"
+    expected: "baṛṣa raāśaira baẏakataimaānae sababhaābarae kañajausa kaimabaā kaṛpaṇa nauhanatai"
+  - source: "ନବନିଯୁକ୍ତ ଓଡିଶା କଂଗ୍ରେସ ପ୍ରଭାରୀ ଏ.ଚେଲ୍ଲା କୁମାରଙ୍କୁ କରୋନା"
+    expected: "nabanaiyaukata oḍaiśaā kaṁgaraesa parabhaāraī e.caelalaā kaumaāraṅakau karaonaā"
+  - source: "ଦିଲ୍ଲୀ: ଦିନ ଦ୍ବିପହରରେ ଗାଡ଼ି ଉପରକୁ ଦୁର୍ବୃତ୍ତ ଚଳାଇଲେ ୮ ରାଉଣ୍ଡ ଗୁଳି: ଚାଳକଙ୍କ ମୃତ୍ୟୁ"
+    expected: "dailalaī: daina dabaipahararae gaāṛai uparakau daurabaṛtata caḷaāilae ୮ raāuṇaḍa gauḷai: caāḷakaṅaka maṛtaẏau"
+  - source: "ବୟସରେ ଆର ପାରିକୁ ଚାଲିଗଲେ କଣ୍ଠଶିଳ୍ପୀ ଅନୁରାଧା ପୋଡୱାଲଙ୍କ ପୁଅ ଆଦିତ୍ୟ"
+    expected: "baẏasarae āra paāraikau caālaigalae kaṇaṭhaśaiḷapaī anauraādhaā paeāḍawaālaṅaka paua ādaitaẏa"
+
+map:
+
+
+  characters:
+    'ଅ': 'a'
+    'ଆ': 'ā'
+    'ଇ': 'i'
+    'ଈ': 'ī'
+    'ଉ': 'u'
+    'ଊ': 'ū'
+    'ଋ': 'ṛ'
+    'ୠ': 'ṝ'
+    'ଌ': 'ḷ'
+    'ୡ': 'ḹ'
+    'ଏ': 'e'
+    'ଐ': 'ai'
+    'ଓ': 'o'
+    'ଔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'କ': 'ka'
+    'ଖ': 'kha'
+    'ଗ': 'ga'
+    'ଘ': 'gha'
+    'ଙ': 'ṅa'
+
+    # Palatals
+    'ଚ': 'ca'
+    'ଛ': 'cha'
+    'ଜ': 'ja'
+    'ଝ': 'jha'
+    'ଞ': 'ña'
+
+    # Cerebrals
+    'ଟ':  'ṭa'
+    'ଠ':  'ṭha'
+    'ଡ':  'ḍa'
+    'ଡ଼':  'ṛa'
+    'ଢ':  'ḍha'
+    'ଢ଼':  'ṛha'
+    'ଣ':  'ṇa'
+
+    # Dentals
+    'ତ': 'ta'
+    'ଥ': 'tha'
+    'ଦ': 'da'
+    'ଧ': 'dha'
+    'ନ': 'na'
+
+    # Labials
+    'ପ': 'pa'
+    'ଫ': 'pha'
+    'ବ': 'ba'
+    'ଭ': 'bha'
+    'ମ': 'ma'
+
+    # Semivowels
+    'ଯ': 'ya'
+    'ୟ': 'ẏa'
+    'ର': 'ra'
+    'ଲ': 'la'
+    'ଳ': 'ḷa'
+    'ଵ': 'va'
+
+    # Sibilants
+    'ଶ': 'śa'
+    'ଷ': 'ṣa'
+    'ସ': 'sa'
+
+    'ୱ': 'wa'
+
+
+    # Aspirate
+    'ହ': 'ha'
+
+    # Chandrabindu
+    'ଁ': 'm̐'
+
+    # Bisarga
+    'ଃ': 'ḥ'
+
+    # Anusvāra
+    'ଂ': 'ṁ'
+
+    # Medials # Needed for connecting constants
+
+    'ା': 'ā'
+    'ି': 'i'
+    'ୀ': 'ī'
+    'ୁ': 'u'
+    'ୂ': 'ū'
+    '\u0B43': 'ṛ'
+    '\u0B44': 'ṝ'
+    '\u0B62': 'ḷ'
+    '\u0B63': 'ḹ'
+    'େ': 'e'
+    'ୈ': 'ai'
+    'ୋ': 'o'
+    'ୌ': 'au'
+
+    # Abagraha
+    'ଽ': ':’'
+
+    '्': ''
+    '୍': ''
+    '़': ''
+    '଼': ''
+    '।': '.'
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining
+
+    # for semivowel rule no. 5
+
+    'ଯଁ': 'm̐ya'
+    'ୟଁ': 'm̐ẏa'
+    'ରଁ': 'm̐ra'
+    'ଲଁ': 'm̐la'
+    'ଳଁ': 'm̐ḷa'
+    'ଵଁ': 'm̐va'

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

@@ -0,0 +1,222 @@
+---
+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:
+  - source: "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ"
+    expected: "paṁjaāba 'ca vadha raihaā ḵẖaudakauśaīāṃ daā raujhaāna"
+  - source: "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ"
+    expected: "lakha taoṃ paāra paujaā saragarama kaesaāṃ daā aṁkaṛaā, dailaī 'ca dao lakha taoṃ paāra inaphaaikaṭaiḍa"
+  - source: "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ"
+    expected: "paraivaāraka samasaiāvaāṃ atae vaiāha vaī haai haora ahaima kaārana"
+  - source: "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ"
+    expected: "maradaāṃ 'ca aurataāṃ naālaoṃ vadha haai ḵẖaudakauśaī daā raujhaāna"
+  - source: "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ"
+    expected: "raāśaṭaraī padhara 'tae paṁjaāba daī sathaitaī kaāfaī saūbaiāṃ taoṃ baihatara"
+  - source: "ਚੀਨੀ ਸੈਨਾ ਨੇ ਲਾਪਤਾ ਅਰੁਣਾਚਲ ਦੇ 5 ਨੌਜਵਾਨਾਂ ਬਾਰੇ ਦੱਸਿਆ"
+    expected: "caīnaī saainaā nae laāpataā arauṇaācala dae 5 naaujavaānaāṃ baārae dasaiā"
+  - source: "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ"
+    expected: "saākharataā dae maāmalae 'ca daeśa 'ca 7vaeṃ naṁbara 'tae paṁjaāba"
+  - source: "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ"
+    expected: "dailaī kamaeṭaī dae maaiṃbara śaṁṭaī nae akaālaī dala taoṃ daitaā asataīfaā"
+  - source: "੧੦੨ ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ"
+    expected: "102 haora kaoraonaā paāzaīṭaiva maraīzaāṃ daī pauśaṭaī, ika daī maauta"
+  - source: "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ"
+    expected: "saṛaka haādasae daauraāna ika daī maauta"
+  - source: "ਅਸੀਂ ਲੁੱਕ ਛੁੱਪ ਕ਼ ਆਪਣੀ ਜਾਨ"
+    expected: "asaīṃ lauka chaupa qa āpaṇaī jaāna"
+
+map:
+
+  characters:
+
+    # Vowels
+
+    'ਅ': 'a'
+    'ਆ': 'ā'
+    'ਇ': 'i'
+    'ਈ': 'ī'
+    'ਉ': 'u'
+    'ਊ': 'ū'
+    'ਏ': 'e'
+    'ਐ': 'ai'
+    'ਓ': 'o'
+    'ਔ': 'au'
+
+    # Consonants
+    # Gutturals
+    'ਕ': 'ka'
+    'ਖ': 'kha'
+    'ਗ': 'ga'
+    'ਘ': 'gha'
+    'ਙ': 'ṅa'
+
+    # Palatals
+    'ਚ': 'ca'
+    'ਛ': 'cha'
+    'ਜ': 'ja'
+    'ਝ': 'jha'
+    'ਞ': 'ña'
+
+    # Cerebrals
+    'ਟ': 'ṭa'
+    'ਠ': 'ṭha'
+    'ਡ': 'ḍa'
+    'ਢ': 'ḍha'
+    'ਣ': 'ṇa'
+
+    # Dentals
+    'ਤ': 'ta'
+    'ਥ': 'tha'
+    'ਦ': 'da'
+    'ਧ': 'dha'
+    'ਨ': 'na'
+
+    # Labials
+    'ਪ': 'pa'
+    'ਫ': 'pha'
+    'ਬ': 'ba'
+    'ਭ': 'bha'
+    'ਮ': 'ma'
+
+    # Semivowels
+    'ਯ': 'ya'
+    'ਰ': 'ra'
+    'ਲ': 'la'
+    'ਲ਼': 'ḷa'
+    'ਵ': 'va'
+    'ੜ': 'ṛa'
+
+    # Sibilants
+    'ਸ': 'sa'
+
+    # Aspirate
+    'ਹ': 'ha'
+
+    # Bindī
+    'ਂ': 'ṃ'
+
+    # Ṭippī
+    'ੰ': 'ṁ'
+
+    # Bisarga
+    'ਃ': 'ḥ'
+
+    # candrabindu
+    '\u0A01': 'm̐'
+
+
+    # Medials # Needed for connecting constants
+    'ਾ': "ā"
+    'ਿ': "i"
+    'ੀ': "ī"
+    'ੁ': "u"
+    'ੂ': "ū"
+    'ੇ': "e"
+    'ੈ': "ai"
+    'ੋ': "o"
+    'ੌ': "au"
+    'ੱ': ""
+
+    # For adhik before a vowel rule 9 exception
+
+    'ੱਅ': ':a'
+    'ੱਆ': ':ā'
+    'ੱਇ': ':i'
+    'ੱਈ': ':ī'
+    'ੱਉ': ':u'
+    'ੱਊ': ':ū'
+    'ੱਏ': ':e'
+    'ੱਐ': ':ai'
+    'ੱਓ': ':o'
+    'ੱਔ': ':au'
+
+    'ੱਾ': ":ā"
+    'ੱਿ': ":i"
+    'ੱੀ': ":ī"
+    'ੱੁ': ":u"
+    'ੱੂ': ":ū"
+    'ੱੇ': ":e"
+    'ੱੈ': ":ai"
+    'ੱੋ': ":o"
+    'ੱੌ': ":au"
+
+
+    # rule 9 exception for bindi and tippi
+
+    'ਂਈ' : 'ī:ṃ'
+    'ੰਈ' : 'ī:ṁ'
+
+
+    # digits
+
+    '੦': '0'
+    '੧': '1'
+    '੨': '2'
+    '੩': '3'
+    '੪': '4'
+    '੫': '5'
+    '੬': '6'
+    '੭': '7'
+    '੮': '8'
+    '੯': '9'
+
+
+    # Perso-Arabic Characters
+
+    'ਖ਼': 'ḵẖa'
+    'ਕ਼': 'qa'
+    'ਗ਼': 'ġa'
+    'ਫ਼': 'fa'
+    'ਸ਼': 'śa'
+    'ਜ਼': 'za'