interscript 0.1.1 → 0.1.6

data/maps/alalc-mar-Deva-Latn-1997.yaml

@@ -0,0 +1,170 @@
+---
+authority_id: alalc
+id: 1997
+language: hin
+source_script: Deva
+destination_script: Latn
+name: Marathi Romanization, 1997
+url: https://www.loc.gov/catdir/cpso/romanization/marathi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Marathi
+
+notes:
+
+  - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+
+  - |
+    The vowel a is implicit after all consonants and consonant clusters and is supplied in
+    transliteration, with the following exceptions:
+
+    a) when another vowel is indicated by its appropriate sign; and
+    b) when the absence of any vowel is indicated by the subscript sign ( ् ) called halanta or
+       virāma.
+
+  - |
+    Exception: Anusvāra is transliterated by:
+
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+    In other circumstances it is transliterated by a tilde (~) over the vowel.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "ठाणे - जिल्ह्यात बुधवारी एक हजार रुग्णांची वाढ, तर जणांच्या मृत्यूची नोंद"
+    expected: "ṭhaāṇae - jailahayaāta baudhavaāraī eka hajaāra raugaṇaāñcaī vaāḍha, tara jaṇaāñcayaā maṛitayaūcaī naonda"
+  - source: "एकता कपूर पुन्हा अडकली वादात, वेबसीरिजमधल्या 'त्या' सीनमुळे जमावाची घरावर दगडफेक"
+    expected: "ekataā kapaūra paunahaā aḍakalaī vaādaāta, vaebasaīraijamadhalayaā 'tayaā' saīnamaulae jamaāvaācaī gharaāvara dagaḍaphaeka"
+  - source: "जाणून घ्या, बीएमसीच्या अधिकाऱ्यांनी कंगना राणौतच्या ऑफिसमधले नक्की काय- काय तोडलं"
+    expected: "jaāṇaūna ghayaā, baīemasaīcayaā adhaikaāऱyaānnaī kaṅganaā raāṇaautacayaā ôphaisamadhalae nakakaī kaāya- kaāya taoḍalam"
+  - source: "कंगना मुंबईत दाखल होण्यापूर्वी 'मातोश्री'वरून फर्मान सुटले; प्रवक्त्यांना सक्त आदेश"
+    expected: "kaṅganaā maumbaīta daākhala haoṇayaāpaūravaī 'maātaośaraī'varaūna pharamaāna sauṭalae; paravakatayaānnaā sakata ādaeśa"
+  - source: "मराठा आरक्षणास तात्पुरती स्थगिती; सर्वोच्च न्यायालयाचा निर्णय"
+    expected: "maraāṭhaā ārakashaṇaāsa taātapaurataī sathagaitaī; saravaocaca nayaāyaālayaācaā nairaṇaya"
+  - source: "भारताच्या तिन्ही लशींचा पहिला टप्पा यशस्वी, वाचा कधी येणार बाजारात"
+    expected: "bhaārataācayaā tainahaī laśaīñcaā pahailaā ṭapapaā yaśasavaī, vaācaā kadhaī yaeṇaāra baājaāraāta"
+  - source: "रुग्णवाढीमुळे खाटांची चणचण"
+    expected: "raugaṇavaāḍhaīmaulae khaāṭaāñcaī caṇacaṇa"
+  - source: "पीएम स्वनिधी कर्ज योजनेला मुंबईतून अल्प प्रतिसाद"
+    expected: "paīema savanaidhaī karaja yaojanaelaā maumbaītaūna alapa parataisaāda"
+  - source: "सांताक्रूझ-चेंबूर लिंक रोडवरील उन्नत मार्गाला स्थगिती"
+    expected: "saāntaākaraūjha-caembaūra laiṅka raoḍavaraīla unanata maāragaālaā sathagaitaī"
+  - source: "संपादक अर्णब गोस्वामी यांच्याविरूद्ध खडक पोलिस ठाण्यात तक्रार"
+    expected: "sampaādaka araṇaba gaosavaāmaī yaāñcayaāvairaūdadha khaḍaka paolaisa ṭhaāṇayaāta takaraāra"
+
+map:
+
+  rules:
+    # note[3]
+    - pattern: \u0902(?=[कखगघङ])
+      result: ṅ
+    - pattern: \u0902(?=[चछजझञ])
+      result: ñ
+    - pattern: \u0902(?=[टठडढण])
+      result: ṇ
+    - pattern: \u0902(?=[तथदधन])
+      result: n
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ऋ': 'ṛ'
+    'ॠ': 'ṝ'
+    'ऌ': 'ḹ'
+    #'ॳ': 'ĕ'
+    'ए': 'e'
+    'ॲ': 'ê'
+    #'अै': 'ai'
+    'ऐ': 'ai'
+    #'ऒ': 'ŏ'
+    'ओ': 'o'
+    'ऑ': 'ô'
+    'औ': 'ău'
+
+    # II. Consonants
+    # Gutturals
+    'क': 'ka'
+    'ख': 'kha'
+    'ग': 'ga'
+    'घ': 'gha'
+    'ङ': 'ṅa'
+
+    # Palatals
+    'च': 'ca'
+    'छ': 'cha'
+    'ज': 'ja'
+    'झ': 'jha'
+    'ञ': 'ña'
+
+    # Cerebrals
+    'ट': 'ṭa'
+    'ठ': 'ṭha'
+    'ड': 'ḍa'
+    #'ड़': 'ṛa'
+    'ढ': 'ḍha'
+    #'ढ़': 'ṛha'
+    'ण': 'ṇa'
+
+    # Dentals
+    'त': 'ta'
+    'थ': 'tha'
+    'द': 'da'
+    'ध': 'dha'
+    'न': 'na'
+
+    # Labials
+    'प': 'pa'
+    'फ': 'pha'
+    'ब': 'ba'
+    'भ': 'bha'
+    'म': 'ma'
+
+    # Semivowels
+    'य': 'ya'
+    'र': 'ra'
+    'ल': 'la'
+    'ळ': 'la'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'śa'
+    'ष': 'sha'
+    'स': 'sa'
+
+    # Aspirate
+    'ह': 'ha'
+
+    # Anusvāra
+    'ं': 'm'
+
+    # Bisarga
+    'ः ': 'ḥ'
+
+    # Abagraha
+    'ऽ': '’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛi"
+    'ॄ': "rī"
+    'े': "e"
+    'ो': "o"
+    'ौ': "au"
+    '्': ''

data/maps/alalc-mkd-Cyrl-Latn-1997.yaml

@@ -0,0 +1,114 @@
+---
+authority_id: alalc
+id: 1997
+language: mkd
+source_script: Cyrl
+destination_script: Latn
+name: Serbian and Makedonian Romanization, ALA-LC 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/serbian.pdf
+creation_date: 1997
+description: ALA-LC Romanization table for Serbian and Makedonian.
+
+notes:
+  - Special characters in romanization
+    Đ - D with crossbar (upper case). USMARC hexadecimal code A3.
+    đ - d with crossbar (upper case). USMARC hexadecimal code B3.
+
+  - Character modifiers in romanization
+    ´ - acute. USMARC hexadecimal code E2.
+    ˇ - hachek. USMARC hexadecimal code E9.
+
+tests:
+  - source: Општина Ердут
+    expected: Opština Erdut
+  - source: Општина Двор
+    expected: Opština Dvor
+  - source: ЛУЃЕ луѓе
+    expected: LUǴE luǵe
+  - source: ЅВЕЗДА ѕвезда Ѕвезда
+    expected: DZVEZDA dzvezda Dzvezda
+  - source: ЌАРУВАЊЕ ќарување
+    expected: ḰARUVANJE ḱaruvanje
+
+map:
+  postrules:
+    # DZ
+    - pattern: "((?<=[[:upper:]])Dz(?=[[:upper:]])?|(?<=[[:upper:]])?Dz(?=[[:upper:]]))"
+      result: "DZ"
+    #LJ
+    - pattern: "((?<=[[:upper:]])Lj(?=[[:upper:]])?|(?<=[[:upper:]])?Lj(?=[[:upper:]]))"
+      result: "LJ"
+    #NJ
+    - pattern: "((?<=[[:upper:]])Nj(?=[[:upper:]])?|(?<=[[:upper:]])?Nj(?=[[:upper:]]))"
+      result: "NJ"
+    #DŽ
+    - pattern: "((?<=[[:upper:]])Dž(?=[[:upper:]])?|(?<=[[:upper:]])?Dž(?=[[:upper:]]))"
+      result: "DŽ"
+
+  characters:
+    "\u0410": "A"
+    "\u0411": "B"
+    "\u0412": "V"
+    "\u0413": "G"
+    "\u0403": "\u01F4" # Ǵ
+    "\u0414": "D"
+    "\u0402": "\u0110" # Đ
+    "\u0415": "E"
+    "\u0416": "\u005a\u030c" # Ž
+    "\u0417": "Z"
+    "\u0405": "Dz"
+    "\u0418": "I"
+    "\u0408": "J"
+    "\u041A": "K"
+    "\u040C": "\u1E30" # Ḱ
+    "\u041B": "L"
+    "\u0409": "Lj"
+    "\u041C": "M"
+    "\u041D": "N"
+    "\u040A": "Nj"
+    "\u041E": "O"
+    "\u041F": "P"
+    "\u0420": "R"
+    "\u0421": "S"
+    "\u0422": "T"
+    "\u040B": "\u0043\u0301" # Ć
+    "\u0423": "U"
+    "\u0424": "F"
+    "\u0425": "H"
+    "\u0426": "C"
+    "\u0427": "\u0043\u030c" # Č
+    "\u040F": "D\u007a\u030c" # Dž
+    "\u0428": "\u0053\u030c" # Š
+    "\u0430": "a"
+    "\u0431": "b"
+    "\u0432": "v"
+    "\u0433": "g"
+    "\u0453": "\u01F5" # ǵ
+    "\u0434": "d"
+    "\u0452": "\u0111" # đ
+    "\u0435": "e"
+    "\u0436": "\u007a\u030c" # ž
+    "\u0437": "z"
+    "\u0455": "dz"
+    "\u0438": "i"
+    "\u0458": "j"
+    "\u043A": "k"
+    "\u045C": "\u1E31" # ḱ
+    "\u043B": "l"
+    "\u0459": "lj"
+    "\u043C": "m"
+    "\u043D": "n"
+    "\u045A": "nj"
+    "\u043E": "o"
+    "\u043F": "p"
+    "\u0440": "r"
+    "\u0441": "s"
+    "\u0442": "t"
+    "\u045B": "\u0063\u0301" # ć
+    "\u0443": "u"
+    "\u0444": "f"
+    "\u0445": "h"
+    "\u0446": "c"
+    "\u0447": "\u0063\u030c" # č
+    "\u045F": "d\u007a\u030c" # dž
+    "\u0448": "\u0073\u030c" # š

data/maps/alalc-mkd-Cyrl-Latn-2013.yaml

@@ -0,0 +1,103 @@
+---
+authority_id: alalc
+id: 2013
+language: mkd
+source_script: Cyrl
+destination_script: Latn
+name: Makedonian Romanization, ALA-LC 2013 System
+url: https://www.loc.gov/catdir/cpso/romanization/macedonian.pdf
+creation_date: 2013
+description: ALA-LC Romanization table for Makedonian.
+
+tests:
+  - source: Општина Ердут
+    expected: Opština Erdut
+  - source: Општина Двор
+    expected: Opština Dvor
+  - source: ЛУЃЕ луѓе
+    expected: LUǴE luǵe
+  - source: ЅВЕЗДА ѕвезда Ѕвезда
+    expected: DZVEZDA dzvezda Dzvezda
+  - source: ЌАРУВАЊЕ ќарување
+    expected: ḰARUVANJE ḱaruvanje
+
+map:
+  postrules:
+    # DZ
+    - pattern: "((?<=[[:upper:]])Dz(?=[[:upper:]])?|(?<=[[:upper:]])?Dz(?=[[:upper:]]))"
+      result: "DZ"
+    #LJ
+    - pattern: "((?<=[[:upper:]])Lj(?=[[:upper:]])?|(?<=[[:upper:]])?Lj(?=[[:upper:]]))"
+      result: "LJ"
+    #NJ
+    - pattern: "((?<=[[:upper:]])Nj(?=[[:upper:]])?|(?<=[[:upper:]])?Nj(?=[[:upper:]]))"
+      result: "NJ"
+    #DŽ
+    - pattern: "((?<=[[:upper:]])Dž(?=[[:upper:]])?|(?<=[[:upper:]])?Dž(?=[[:upper:]]))"
+      result: "DŽ"
+
+  characters:
+    "\u0410": "A"
+    "\u0411": "B"
+    "\u0412": "V"
+    "\u0413": "G"
+    "\u0403": "\u01F4" # Ǵ
+    "\u0414": "D"
+    "\u0402": "\u0110" # Đ
+    "\u0415": "E"
+    "\u0416": "\u005a\u030c" # Ž
+    "\u0417": "Z"
+    "\u0405": "Dz"
+    "\u0418": "I"
+    "\u0408": "J"
+    "\u041A": "K"
+    "\u040C": "\u1E30" # Ḱ
+    "\u041B": "L"
+    "\u0409": "Lj"
+    "\u041C": "M"
+    "\u041D": "N"
+    "\u040A": "Nj"
+    "\u041E": "O"
+    "\u041F": "P"
+    "\u0420": "R"
+    "\u0421": "S"
+    "\u0422": "T"
+    "\u0423": "U"
+    "\u0424": "F"
+    "\u0425": "H"
+    "\u0426": "C"
+    "\u0427": "\u0043\u030c" # Č
+    "\u040F": "D\u007a\u030c" # Dž
+    "\u0428": "\u0053\u030c" # Š
+    "\u0430": "a"
+    "\u0431": "b"
+    "\u0432": "v"
+    "\u0433": "g"
+    "\u0453": "\u01F5" # ǵ
+    "\u0434": "d"
+    "\u0452": "\u0111" # đ
+    "\u0435": "e"
+    "\u0436": "\u007a\u030c" # ž
+    "\u0437": "z"
+    "\u0455": "dz"
+    "\u0438": "i"
+    "\u0458": "j"
+    "\u043A": "k"
+    "\u045C": "\u1E31" # ḱ
+    "\u043B": "l"
+    "\u0459": "lj"
+    "\u043C": "m"
+    "\u043D": "n"
+    "\u045A": "nj"
+    "\u043E": "o"
+    "\u043F": "p"
+    "\u0440": "r"
+    "\u0441": "s"
+    "\u0442": "t"
+    "\u0443": "u"
+    "\u0444": "f"
+    "\u0445": "h"
+    "\u0446": "c"
+    "\u0447": "\u0063\u030c" # č
+    "\u045F": "d\u007a\u030c" # dž
+    "\u0448": "\u0073\u030c" # š

data/maps/alalc-pan-Deva-Latn-1997.yaml

@@ -0,0 +1,237 @@
+---
+authority_id: alalc
+id: 1997
+language: pan
+source_script: Deva
+destination_script: Latn
+name: Panjabi Romanization, 1997
+url: https://www.loc.gov/catdir/cpso/romanization/panjabi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Panjabi
+
+notes:
+
+  - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+
+  - |
+    The vowel a is implicit after consonant clusters and may be implicit after consonants except
+    when they are final or when another vowel is indicated by its appropriate sign. The cases in
+    which the vowel a is implicit, however, can be determined only from a knowledge of the
+    language or from suitable reference sources. In such cases the a is supplied in transliteration.
+
+  - The dotted letters (ਸ਼ ਖ਼ ਗ਼ ਜ਼ ਫ਼ ਲ਼) are used in Urdu words.
+
+  - |
+    Exception: Bindī is transliterated by:
+
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+
+  - |
+    Exception: Ṭippī is transliterated by:
+
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+
+  - |
+    Exception: When adhik implies the combination of a non-aspirated and an aspirated
+    consonant, the combination is transliterated as a non-aspirated, followed by an aspirated
+    consonant.
+
+tests:
+  - source: "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ"
+    expected: "pañjaāba 'ca wadha raihaā khaudakaushaīāṃ daā raujhaāna"
+  - source: "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ"
+    expected: "lakkha taoṃ paāra paujjaā saragarama kaesaāṃ daā aṅkaṛaā, daillaī 'ca dao lakkha taoṃ paāra inaphaaikaṭaiḍa"
+  - source: "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ"
+    expected: "paraiwaāraka samassaiāwaāṃ atae waiāha waī haai haora ahaima kaārana"
+  - source: "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ"
+    expected: "maradaāṃ 'ca aurataāṃ naālaoṃ waddha haai khaudakaushaī daā raujhaāna"
+  - source: "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ"
+    expected: "raāshaṭaraī paddhara 'tae pañjaāba 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 naaujawaānaāṃ baārae dassaiā"
+  - source: "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ"
+    expected: "saākharataā dae maāmalae 'ca daesha 'ca 7waeṃ nam̆̐bara 'tae pañjaāba"
+  - source: "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ"
+    expected: "daillaī kamaeṭaī dae maaiṃbara shaṇṭaī nae akaālaī dala taoṃ daittaā asataīfaā"
+  - source: "102 ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ"
+    expected: "102 haora kaoraonaā paāzaīṭaiwa maraīzaāṃ daī paushaṭaī, ika daī maauta"
+  - source: "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ"
+    expected: "saṛaka haādasae daauraāna ika daī maauta"
+
+map:
+
+  rules:
+    # note[4]
+    - pattern: \u0A02(?=[ਕਖਖ਼ਗਗ਼ਘਙ])    # ਂ  before gutturals
+      result: ṅ
+    - pattern: \u0A02(?=[ਚਛਜਜ਼ਝਞ])    # ਂ   before palatals
+      result: ñ
+    - pattern: \u0A02(?=[ਟਠਡਢਣ])    # ਂ   before cerebrals
+      result: ṇ
+    - pattern: \u0A02(?=[ਤਥਦਧਨ])    # ਂ   before dentals
+      result: n
+
+    # note[5]
+    - pattern: \u0A70(?=[ਕਖਖ਼ਗਗ਼ਘਙ])    # ੰ  before gutturals
+      result: ṅ
+    - pattern: \u0A70(?=[ਚਛਜਜ਼ਝਞ])    # ੰ  before palatals
+      result: ñ
+    - pattern: \u0A70(?=[ਟਠਡਢਣ])    # ੰ  before cerebrals
+      result: ṇ
+    - pattern: \u0A70(?=[ਤਥਦਧਨ])    # ੰ  before dentals
+      result: n
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'ਅ': 'a'
+    'ਆ': 'ā'
+    'ਇ': 'i'
+    'ਈ': 'ī'
+    'ਉ': 'u'
+    'ਊ': 'ū'
+    'ਏ': 'e'
+    'ਐ': 'ai'
+    'ਓ': 'o'
+    'ਔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ਕ': 'ka'
+    'ਖ': 'kha'
+    'ਖ਼': 'kha'
+    'ਗ': 'ga'
+    'ਗ਼': 'gha'
+    'ਘ': 'gha'
+    'ਙ': 'ṅa'
+
+    # Palatals
+    'ਚ': 'ca'
+    'ਛ': 'cha'
+    'ਜ਼': 'za'
+    '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'
+    'ਫ਼': 'fa'
+    'ਬ': 'ba'
+    'ਭ': 'bha'
+    'ਮ': 'ma'
+
+    # Semivowels
+    'ਯ': 'ya'
+    'ਰ': 'ra'
+    'ਲ': 'la'
+    'ਲੵ': 'ḷa'
+    'ਲ਼': 'ḷa'
+    'ਵ': 'wa'
+    'ੜ': 'ṛa'
+
+    # Sibilants
+    'ਸ': 'sa'
+    'ਸ਼': 'sha'
+
+    # Aspirate
+    'ਹ': 'ha'
+
+    # Bindī (see Note 4)
+    'ਂ': 'ṃ'
+
+    # Ṭippī (see Note 5)
+    'ੰ': 'm̆̐'
+
+    # Medials # Needed for connecting constants
+    'ਾ': "ā"
+    'ਿ': "i"
+    'ੀ': "ī"
+    'ੁ': "u"
+    'ੂ': "ū"
+    'ੇ': "e"
+    'ੈ': "ai"
+    'ੋ': "o"
+    'ੌ': "au"
+
+    # For adhik character[Note 6]
+
+    # Gutturals
+    'ੱਕ': 'kka'
+    'ੱਖ': 'kkha'
+    'ੱਖ਼': 'kkha'
+    'ੱਗ': 'gga'
+    'ੱਗ਼': 'ggha'
+    'ੱਘ': 'ggha'
+    'ੱਙ': 'ṅṅa'
+
+    # Palatals
+    'ੱਚ': 'cca'
+    'ੱਛ': 'ccha'
+    'ੱਜ': 'jja'
+    'ੱਜ਼': 'zza'
+    'ੱਝ': 'jjha'
+    'ੱਞ': 'ñña'
+
+    # Cerebrals
+    'ੱਟ': 'ṭṭa'
+    'ੱਠ': 'ṭṭha'
+    'ੱਡ': 'ḍḍa'
+    'ੱਢ': 'ḍḍha'
+    'ੱਣ': 'ṇṇa'
+
+    # Dentals
+    'ੱਤ': 'tta'
+    'ੱਥ': 'ttha'
+    'ੱਦ': 'dda'
+    'ੱਧ': 'ddha'
+    'ੱਨ': 'nna'
+
+    # Labials
+    'ੱਪ': 'ppa'
+    'ੱਫ': 'ppha'
+    'ੱਫ਼': 'ffa'
+    'ੱਬ': 'bba'
+    'ੱਭ': 'bbha'
+    'ੱਮ': 'mma'
+
+    # Semivowels
+    'ੱਯ': 'yya'
+    'ੱਰ': 'rra'
+    'ੱਲ': 'lla'
+    'ੱਲੵ': 'ḷḷa'
+    'ੱਵ': 'wwa'
+    'ੱੜ': 'ṛṛa'
+
+    # Sibilants
+    'ੱਸ': 'ssa'
+    'ੱਸ਼': 'ssha'
+
+    # Aspirate
+    'ੱਹ': 'hha'