interscript 0.1.1 → 0.1.6

data/maps/bis-ori-Orya-Latn-13194-1991.yaml

@@ -0,0 +1,160 @@
+---
+authority_id: bis
+id: 1991
+language: ori
+source_script: Orya
+destination_script: Latn
+name: Indian script code for information interchange - ISCII - Oriya Romanization
+#url:
+creation_date: 1991
+description: |
+  IS 13194 (1991): Indian script code for information
+  interchange - ISCII [LITD 20: Indian Language Technologies
+  and Products]
+
+notes:
+  - |
+    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.
+
+tests:
+  - source: "ସାମ୍ପ୍ରତିକ ବିଶ୍ବ ସ୍ଥିତାବସ୍ଥାକୁ ଚାଲେଞ୍ଜ୍‌ କରୁଥିବା ଦୁଇ ମୁଖ୍ୟ ପ୍ରତିଦ୍ବନ୍ଦ୍ବୀ ହେଉଛନ୍ତି ଚୀନ୍‌ ଓ ରୁଷ୍: ଇଂଲଣ୍ଡ୍‌ ଗୁଇନ୍ଦା ଅଧିକାରୀ"
+    expected: "sāmprtik biśb sthitābsthāku cālēñj kruthibā dui mukhẏ prtidbndbī hēuchnti cīn ŏ ruṣ: iṃlṇḍ guindā adhikārī"
+  - source: "ଏଣିକି ଏହି ଗାଡ଼ି ଚଳାଇଲେ ପୁଲିସ କାଟି ପାରିବ ନାହିଁ ଫାଇନ୍"
+    expected: "ēṇiki ēhi gād̂i cḷāilē pulis kāṭi pārib nāhim phāin"
+  - source: "ପିସି କାରବାର ଘଟଣା, ନିଲମ୍ବନ ହେଲେ ପଞ୍ଚାୟତ ଅଧିକାରୀ"
+    expected: "pisi kārbār ghṭṇā, nilmbn hēlē pñcāẏt adhikārī"
+  - source: "ବରିଷ୍ଠ ଓଡ଼ିଆ ଚଳଚ୍ଚିତ୍ର ଅଭିନେତା ଅଜିତ ଦାସଙ୍କ"
+    expected: "briṣṭh ŏḍiā cḷccitr abhinētā ajit dāsṅk"
+  - source: "ସଞ୍ଚୟ କରିବାରେ କେଉଁ ରାଶି ଅଧିକ ସତର୍କ ?"
+    expected: "sñcẏ kribārē kēum rāśi adhik strk ?"
+  - source: "କର୍କଟ ରାଶିର ଅଧିକାରୀ ନିଜ ଜ୍ଞାତିପରିଜନଙ୍କ ପାଇଁ ଟଙ୍କା ଖର୍ଚ୍ଚ କରିବାକୁ ପସନ୍ଦ କରିଥାନ୍ତି।"
+    expected: "krkṭ rāśir adhikārī nij jñātiprijnṅk pāim ṭṅkā khrcc kribāku psnd krithānti."
+  - source: "ବୃଷ ରାଶିର ବ୍ୟକ୍ତିମାନେ ସ୍ବଭାବରେ କଞ୍ଜୁସ୍ କିମ୍ବା କୃପଣ ନୁହନ୍ତି"
+    expected: "bṛṣ rāśir bẏktimānē sbbhābrē kñjus kimbā kṛpṇ nuhnti"
+  - source: "ନବନିଯୁକ୍ତ ଓଡିଶା କଂଗ୍ରେସ ପ୍ରଭାରୀ ଏ.ଚେଲ୍ଲା କୁମାରଙ୍କୁ କରୋନା"
+    expected: "nbniyukt ŏḍiśā kṅgrēs prbhārī ē.cēllā kumārṅku krŏnā"
+  - source: "ଦିଲ୍ଲୀ: ଦିନ ଦ୍ବିପହରରେ ଗାଡ଼ି ଉପରକୁ ଦୁର୍ବୃତ୍ତ ଚଳାଇଲେ ୮ ରାଉଣ୍ଡ ଗୁଳି: ଚାଳକଙ୍କ ମୃତ୍ୟୁ"
+    expected: "dillī: din dbiphrrē gād̂i uprku durbṛtt cḷāilē ୮ rāuṇḍ guḷi: cāḷkṅk mṛtẏu"
+  - source: "ବୟସରେ ଆର ପାରିକୁ ଚାଲିଗଲେ କଣ୍ଠଶିଳ୍ପୀ ଅନୁରାଧା ପୋଡୱାଲଙ୍କ ପୁଅ ଆଦିତ୍ୟ"
+    expected: "bẏsrē ār pāriku cāliglē kṇṭhśiḷpī anurādhā pēāḍୱālṅk pua āditẏ"
+
+map:
+
+  rules:
+    # note
+    - pattern: \u0B02(?=[କଖଗଘଙ])
+      result: ṅ
+    - pattern: \u0B02(?=[ଚଛଜଝଞ])
+      result: ñ
+    - pattern: \u0B02(?=[ଟଠଡଡ଼ଢଣଢ଼])
+      result: ṇ
+    - pattern: \u0B02(?=[ତଥଦଧନ])
+      result: n
+    - pattern: \u0B02(?=[ପଫବଭମ])
+      result: m
+
+
+  characters:
+    'ଅ': 'a'
+    'ଆ': 'ā'
+    'ଇ': 'i'
+    'ଈ': 'ī'
+    'ଉ': 'u'
+    'ଊ': 'ū'
+    'ଋ': 'ṛ'
+    'ଌ': 'ḻ'
+    'ଏ': 'ē'
+    'ଐ': 'ai'
+    'ଓ': 'ŏ'
+    'ଔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'କ': 'k'
+    'ଖ': 'kh'
+    'ଗ': 'g'
+    'ଘ': 'gh'
+    'ଙ': 'ṅ'
+
+    # Palatals
+    'ଚ': 'c'
+    'ଛ': 'ch'
+    'ଜ': 'j'
+    'ଝ': 'jh'
+    'ଞ': 'ñ'
+
+    # Cerebrals
+    'ଟ':  'ṭ'
+    'ଠ':  'ṭh'
+    'ଡ':  'ḍ'
+    'ଡ଼':  'd̂'
+    'ଢ':  'ḍh'
+    'ଢ଼':  'd̂h'
+    'ଣ':  'ṇ'
+
+    # Dentals
+    'ତ': 't'
+    'ଥ': 'th'
+    'ଦ': 'd'
+    'ଧ': 'dh'
+    'ନ': 'n'
+
+    # Labials
+    'ପ': 'p'
+    'ଫ': 'ph'
+    'ବ': 'b'
+    'ଭ': 'bh'
+    'ମ': 'm'
+
+    # Semivowels
+    'ଯ': 'y'
+    'ୟ': 'ẏ'
+    'ର': 'r'
+    'ଲ': 'l'
+    'ଳ': 'ḷ'
+    'ଵ': 'v'
+
+    # Sibilants
+    'ଶ': 'ś'
+    'ଷ': 'ṣ'
+    'ସ': 's'
+
+
+    # Aspirate
+    'ହ': 'h'
+
+    # Chandrabindu
+    'ଁ': 'm'
+
+    # Bisarga
+    'ଃ': 'ḥ'
+
+    # Anusvāra
+    'ଂ': 'ṃ'
+
+    # Medials # Needed for connecting constants
+
+    'ା': 'ā'
+    'ି': 'i'
+    'ୀ': 'ī'
+    'ୁ': 'u'
+    'ୂ': 'ū'
+    'ୃ': 'ṛ'
+    'େ': 'ē'
+    'ୈ': 'ai'
+    'ୋ': 'ŏ'
+    'ୌ': 'au'
+
+    '्': ''
+    '୍': ''
+    '़': ''
+    '଼': ''
+    '।': '.'
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining

data/maps/bis-pnj-Guru-Latn-13194-1991.yaml

@@ -0,0 +1,175 @@
+---
+authority_id: bis
+id: 1991
+language: pnj
+source_script: Guru
+destination_script: Latn
+name: Indian script code for information interchange - ISCII - Panjabi(Gurmukhi) Romanization
+#url:
+creation_date: 1991
+description: |
+  IS 13194 (1991): Indian script code for information
+  interchange - ISCII [LITD 20: Indian Language Technologies
+  and Products]
+
+notes:
+  - |
+    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.
+
+tests:
+  - source: "ਸਦਾ ਜਵਾਨ ਰਹੋ"
+    expected: "sdā jvāṉ rhō"
+  - source: "ਸਵਾਮੀ ਅਗਨੀਵੇਸ਼ ਦੀ ਮੌਤ"
+    expected: "svāmī agṉīvēs dī maut"
+  - source: "ਇਸ ਲਈ ਖੱਟੀ ਤਲੀ ਚੀਜ਼ , ਫਾਸਟ ਫੁੂਟ, ਤੇਜ਼ ਮਿਰਚ ਮਸਾਲਿਆਂ ਨੂੰ ਛੱਡਕੇ ਚੰਗੇ ਤੇ ਮੌਸਮੀ ਫਲ, ਹਰੀਆਂ ਸ਼ਬਜ਼ੀਆਂ, ਘਰ ਦੀ ਲੱਸੀ ਤੇ ਦਹੀਂ ਤੇ ਔਰਗੈਨਿਕ ਚੀਜ਼ਾਂ ਹੀ ਅਪਣਾਉ"
+    expected: "is lī khṭī tlī cīz , phāsṭ phuūṭ, tēz mirc msāliān ṉūṃ chḍkē cṅgē tē mausmī phl, hrīān śbzīān, ghr dī lsī tē dhīn tē aurgaiṉik cīzān hī apṇāu"
+  - source: "ਤੁਹਾਡਾ ਚਿਹਰਾ ਸਦਾ ਚੜ੍ਹਦੀ ਕਲਾ ‘ਚ ਰਹਿਣਾ ਤੇ ਹਮੇਸ਼ਾ ਖਿੜੀਆਂ ਰਹਿਣਾ ਤੇ ਠਾਠਾਂ ਮਾਰਦਾ ਸਰੀਰ ਹੀ ਤੁਹਾਡੇ ਜਵਾਨ ਰਹਿਣ ਦੀ ਨਿਸ਼ਾਨੀ ਹੈ"
+    expected: "tuhāḍā cihrā sdā cṛahdī klā ‘c rhiṇā tē hmēśā khiṛaīān rhiṇā tē ṭhāṭhān mārdā srīr hī tuhāḍē jvāṉ rhiṇ dī ṉiśāṉī hai"
+  - source: "ਧੌਲੇ ਆਉਣਾ ਜਾਂ ਕਹਿ ਲਵੋ, ਵਾਲ ਚਿੱਟੇ ਹੋਣਾ ਬੁੱਢਾਪਾ ਨਹੀਂ ਹੈ।ਪਰ ਉਮਰ ਤਂੋ ਪਹਿਲਾਂ ਮੂੰਹ ਤੋਂ ਨੂਰ ਉੜ ਜਾਣਾ,ਹਮੇਸ਼ਾਂ ਥੱਕਿਆ-2 ਰਹਿਣਾ ,ਬਿਮਾਰ ਰਹਿਣਾ ਅਸਲ ਬੁਢਾਪਾ ਹੈ"
+    expected: "dhaulē āuṇā jān khi lvō, vāl ciṭē hōṇā buḍhāpā ṉhīn hai.pr umr tnō philān mūṃh tōn ṉūr uṛa jāṇā,hmēśān thkiā-2 rhiṇā ,bimār rhiṇā asl buḍhāpā hai"
+  - source: "ਇਸ ਲਈ ਇਹ ਆਪਾਂ ਨੂੰ ਦੇਖਣਾ ਪਵੇਗਾ ਕਿ ਆਪਾਂ ਕਿਵੇਂ ਤੰਦਰੁਸਤ ਰਹਿਣਾ ਹੈ ਤੇ ਨਿਰੋਗ ਰਹਿਣਾ ਹੈ"
+    expected: "is lī ih āpān ṉūṃ dēkhṇā pvēgā ki āpān kivēn tndrust rhiṇā hai tē ṉirōg rhiṇā hai"
+  - source: "ਸਮਾਜਿਕ ਕਾਰਕੁੰਨ ਸਵਾਮੀ ਅਗਨੀਵੇਸ ਦਾ ਅੱਜ ਸ਼ਾਮੀਂ ਦਿਹਾਂਤ ਹੋ ਗਿਆ"
+    expected: "smājik kārkunṉ svāmī agṉīvēs dā aj sāmīn dihānt hō giā"
+  - source: "ਹਰ ਇਨਸਾਨ ਸਦਾ ਸਵਸਥ ਤੇ ਜਵਾਨ ਰਹਿਣਾ ਚਾਹੁੰਦਾ ਹੈ"
+    expected: "hr iṉsāṉ sdā svsth tē jvāṉ rhiṇā cāhundā hai"
+  - source: "ਜਨਮ ਲੈਣਾ ਤੇ ਮੌਤ ਇੱਕ ਅਟਲ ਸੱਚਾਈ ਹੈ"
+    expected: "jṉm laiṇā tē maut ik aṭl scāī hai"
+  - source: "ਇਸਦੇ ਉਲਟ ਤੁਹਾਡੀ ਗਲਤ ਜੀਵਨ ਸ਼ੈਲੀ, ਗਲਤ ਖਾਣਾ ਤੇ ਹਮੇਸ਼ਾ ਕੀਮਤੀ ਸਰੀਰ ਪ੍ਰਤੀ ਲਾਪਰਵਾਹੀ ਕਦੇ ਵੀ ਤੁਹਾਨੁੂੰ ਜਵਾਨ ਤੇ ਨਿਰੋਗੀ ਨਹੀਂ ਰੱਖ ਸਕਦੀ"
+    expected: "isdē ulṭ tuhāḍī glt jīvṉ śailī, glt khāṇā tē hmēśā kīmtī srīr prtī lāprvāhī kdē vī tuhāṉuūṃ jvāṉ tē ṉirōgī ṉhīn rkh skdī"
+
+map:
+
+  rules:
+    # note
+    - 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
+    - pattern: \u0A70(?=[ਪਫਬਭਮ])
+      result: m
+
+
+  characters:
+    'ਅ': 'a'
+    'ਆ': 'ā'
+    'ਇ': 'i'
+    'ਈ': 'ī'
+    'ਉ': 'u'
+    'ਊ': 'ū'
+    'ੲ': 'ṛ'
+    'ੳ': 'ṝ'
+    'ਏ': 'ē'
+    'ਐ': 'ai'
+
+    'ਓ': 'ŏ'
+    'ਔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ਕ': 'k'
+    'ਖ': 'kh'
+    'ਗ': 'g'
+    'ਘ': 'gh'
+    'ਙ': 'ṅ'
+
+    # Palatals
+    'ਚ': 'c'
+    'ਛ': 'ch'
+    'ਜ': 'j'
+    'ਝ': 'jh'
+    'ਞ': 'ñ'
+
+    # Cerebrals
+    'ਟ': 'ṭ'
+    'ਠ': 'ṭh'
+    'ਡ': 'ḍ'
+    'ਢ': 'ḍh'
+    'ਣ': 'ṇ'
+
+    # Dentals
+    'ਤ': 't'
+    'ਥ': 'th'
+    'ਦ': 'd'
+    'ੜ': 'ṛa'
+    'ਧ': 'dh'
+    'ਨ': 'ṉ'
+
+    # Labials
+    'ਪ': 'p'
+    'ਫ': 'ph'
+    'ਬ': 'b'
+    'ਭ': 'bh'
+    'ਮ': 'm'
+
+    # Semivowels
+    'ਯ': 'y'
+    #'य़': 'ẏ'
+    'ਰ': 'r'
+    #'ऱ': 'ṟ'
+    'ਲ': 'l'
+    'ਲ਼': 'ḷ'
+    #'ऴ': 'ẕ'
+
+
+    'ਵ': 'v'
+
+    # Sibilants
+    'ਸ਼': 'ś'
+    #'ष': 'ṣ'
+    'ਸ': 's'
+
+
+    # Aspirate
+    'ਹ': 'h'
+
+
+    #Nukta Constants
+
+    'क़': 'q'
+    'ਖ਼': 'ḵẖ'
+    'ਗ਼': 'gẖ'
+    'ਜ਼': 'z'
+    'ਫ਼': 'f'
+
+    # Chandrabindu
+    'ँ': 'm'
+
+    # Bisarga
+    'ः ': 'ḥ'
+    'ਂ': 'n'
+
+    # Anusvāra
+    'ੰ': 'ṃ'
+
+    # Medials # Needed for connecting constants
+    'ਾ': "ā"
+    'ਿ': "i"
+    'ੀ': "ī"
+    'ੁ': "u"
+    'ੂ': "ū"
+    'ृ': "ṛ"
+
+
+    'ੇ': "ē"
+    'ੈ': "ai"
+
+
+    'ੋ': 'ō'
+    'ੌ': 'au'
+
+    '੍': ''
+    '਼': ''
+    'ੱ': ''
+    '।': '.'
+    "‍": '' # no need for zero with joiner

data/maps/bis-tel-Telu-Latn-13194-1991.yaml

@@ -0,0 +1,170 @@
+---
+authority_id: bis
+id: 1991
+language: tel
+source_script: Telu
+destination_script: Latn
+name: Indian script code for information interchange - ISCII - Telegu Romanization
+#url:
+creation_date: 1991
+description: |
+  IS 13194 (1991): Indian script code for information
+  interchange - ISCII [LITD 20: Indian Language Technologies
+  and Products]
+
+notes:
+  - |
+    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.
+
+tests:
+  - source: "ఇప్పుడు ఇదే కోవలో టాలీవుడ్‌లో మరో మల్టీస్టారర్‌ రూపొందనుందని సినీ వర్గాల్లో వార్తలు వినిపిస్తున్నాయి"
+    expected: "ippuḍu idē kŏvlŏ ṭālīvuḍlŏ mrŏ mlṭīsṭārr rūpondnundni sinī vrgāllŏ vārtlu vinipistunnāyi"
+  - source: "అంటే ఉంటాయి, అయితే అవి చాలా పెద్దవై ఉండాల్సిన అవసరం లేదు అంటున్నారు మమ్ముట్టి"
+    expected: "aṇṭē uṇṭāyi, ayitē avi cālā peddvai uṇḍālsin avsrṃ lēdu aṇṭunnāru mmmuṭṭi"
+  - source: "ఆ సంతోషాన్ని అభిమానులతో పంచుకున్నారు"
+    expected: "ā sntŏṣānni abhimānultŏ pñcukunnāru"
+  - source: "కెమెరాను అన్‌బాక్స్‌ చేసే వీడియోను సోషల్‌ మీడియాలో అభిమానులతో పంచుకున్నారు"
+    expected: "kemerānu anbāks cēsē vīḍiyŏnu sŏṣl mīḍiyālŏ abhimānultŏ pñcukunnāru"
+  - source: "ఇన్నాళ్లకు నిజమయింది. ఇక ఇప్పటి నుంచి దీంతో ఫొటోలు క్లిక్‌ మనిపిస్తా’’ అని ఆ వీడియోలో పేర్కొన్నారు"
+    expected: "innāḷlku nijmyindi. ik ippṭi nuñci dīntŏ phoṭŏlu klik mnipistā’’ ani ā vīḍiyŏlŏ pērkonnāru"
+  - source: "గవర్నర్‌తో కంగనా భేటీ"
+    expected: "gvrnrtŏ kṅgnā bhēṭī"
+  - source: "శ్రియ సినిమా సెట్‌లో అడుగుపెట్టి ఆరు నెలలు కావొస్తోంది"
+    expected: "śriy sinimā seṭlŏ aḍugupeṭṭi āru nellu kāvostŏndi"
+  - source: "ఇప్పుడు తను కోరుకున్న కెమెరా చేతికి రావడంతో త్వరలో మమ్ముట్టి నుంచి స్టన్నింగ్‌ ఫొటోస్‌ రావడం ఖాయం అంటున్నారు ఆయన అభిమానులు"
+    expected: "ippuḍu tnu kŏrukunn kemerā cētiki rāvḍntŏ tvrlŏ mmmuṭṭi nuñci sṭnniṅg phoṭŏs rāvḍṃ khāyṃ aṇṭunnāru āyn abhimānulu"
+  - source: "ఇప్పుడు ఆ వీడియో వైరల్‌ అయింది. ‘ఆ కెమెరాను కొనాలనేది చాలాకాలంగా నా కల."
+    expected: "ippuḍu ā vīḍiyŏ vairl ayindi. ‘ā kemerānu konālnēdi cālākālṅgā nā kl."
+  - source: "మరో వైపు ఎన్టీఆర్‌, రామ్‌చరణ్‌ కలిసి ట్రిపుల్‌ ఆర్‌ సినిమాలో నటిస్తున్నారు"
+    expected: "mrŏ vaipu enṭīār, rāmcrṇ klisi ṭripul ār sinimālŏ nṭistunnāru"
+map:
+
+  rules:
+    # note
+    - pattern: \u0C02(?=[కఖగఘఙ])
+      result: ṅ
+    - pattern: \u0C02(?=[చఛజఝఞ])
+      result: ñ
+    - pattern: \u0C02(?=[టఠడఢణ])
+      result: ṇ
+    - pattern: \u0C02(?=[తథదధన])
+      result: n
+    - pattern: \u0C02(?=[పఫబభమ])
+      result: m
+
+
+  characters:
+    'అ': 'a'
+    'ఆ': 'ā'
+    'ఇ': 'i'
+    'ఈ': 'ī'
+    'ఉ': 'u'
+    'ఊ': 'ū'
+    'ఋ': 'ṛ'
+    'ఌ': 'ḻ'
+    'ౡ': 'ḻ'
+    'ఎ': 'e'
+    'ఏ': 'ē'
+    'ఐ': 'ai'
+    'ఒ': 'o'
+    'ఓ': 'ŏ'
+    'ఔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals  క ఖ గ ఘ ఙ
+    'క': 'k'
+    'ఖ': 'kh'
+    'గ': 'g'
+    'ఘ': 'gh'
+    'ఙ': 'ṅ'
+
+    # Palatals చ ఛ జ ఝ ఞ
+    'చ': 'c'
+    'ఛ': 'ch'
+    'జ': 'j'
+    'ఝ': 'jh'
+    'ఞ': 'ñ'
+
+    # Cerebrals ట ఠ డ ఢ ణ
+    'ట':  'ṭ'
+    'ఠ':  'ṭh'
+    'డ':  'ḍ'
+    'ఢ':  'ḍh'
+    'ణ':  'ṇ'
+
+    # Dentals త థ ద ధ న
+    'త': 't'
+    #'ৎ': 't'
+    'థ': 'th'
+    'ద': 'd'
+    'ధ': 'dh'
+    'న': 'n'
+
+    # Labials ప ఫ బ భ మ
+    'ప': 'p'
+    'ఫ': 'ph'
+    'బ': 'b'
+    'భ': 'bh'
+    'మ': 'm'
+
+    # Semivowels య ర ల వ
+    'య': 'y'
+    'ర': 'r'
+    'ఱ': 'ṛ'
+    'ల': 'l'
+    'ళ': 'ḷ'
+    'వ': 'v'
+
+    # Sibilants శ ష స హ
+    'శ': 'ś'
+    'ష': 'ṣ'
+    'స': 's'
+
+
+
+    # Aspirate
+    'హ': 'h'
+
+
+    'క్ష': 'kṣa'
+
+
+    # Chandrabindu
+    'ঁ': 'm'
+
+    # Bisarga
+    'ః': 'ḥ'
+
+    # Anusvāra
+    'ం': 'ṃ'
+
+    # Medials # Needed for connecting constants
+
+    'ా': 'ā'
+    'ి': 'i'
+    'ీ': 'ī'
+    'ు': 'u'
+    'ూ': 'ū'
+    'ృ': 'ṛ'
+    'ె': 'e'
+    'ే': 'ē'
+    'ై': 'ai'
+    'ొ': 'o'
+    'ో': 'ŏ'
+    'ౌ': 'au'
+    '\u09CD': '' # Used for joining
+
+
+    '\u0c4d': '' #verma sign for halanta
+    'ౕ	': ''
+    'ౖ	': ''
+    '्': ''
+    '़': ''
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining