interscript-maps 2.0.5

data/maps/alalc-guj-Gujr-Latn-2011.imp

@@ -0,0 +1,57 @@
+metadata {
+  authority_id: alalc
+  id: 2011
+  language: iso-639-2:guj
+  source_script: Gujr
+  destination_script: Latn
+  name: Gujarati Romanization, 2011
+  url: https://www.loc.gov/catdir/cpso/romanization/gujarati.pdf
+  creation_date: 2011
+  description: |
+    ALA-LC Romanization table for Gujarati
+
+  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 symbol ( ્ ) 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.
+
+    - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+}
+
+tests {
+  test "મોર્ગન અને રસેલ ફ્લોપ રહ્યા", "mȏrgana anȇ rasȇla phlȏpa rahyā"
+  test "રોયલ ચેલેન્જર્સ બેંગલોરના કેપ્ટન વિરાટ કોહલીએ કોલકાતા નાઈટ રાઈડર્સ સામે શારજાહ ખાતે ટોસ જીતીને બેટિંગ લીધી છે.", "rȏyala cȇlȇnjarsa bȇṅgalȏranā kȇpṭana virāṭa kȏhalīȇ kȏlakātā nāīṭa rāīḍarsa sāmȇ śārajāha khātȇ ṭȏsa jītīnȇ bȇṭiṅga līdhī chȇ."
+  test "અમદાવાદમાં ભણી ચૂકેલા શ્રીકાંત દાતાર પ્રતિષ્ઠિત હાર્વર્ડ બિઝનેસ સ્કૂલના ડીન બન્યા", "amadāvādamāṃ bhaṇī cūkȇlā śrīkānta dātāra pratishṭhita hārvarḍa bijhanȇsa skūlanā ḍīna banyā"
+  test "ઓગસ્ટ મહિનામાં મેન્યુફેક્ચરિંગ સેક્ટરનું ઉત્પાદન ગગડ્યુ", "ȏgasṭa mahināmāṃ mȇnyuphȇkcariṅga sȇkṭaranuṃ utpādana gagaḍyu"
+  test "૯૦ વર્ષમાં બે કરોડમાંથી પોણાબે લાખ કરોડ થઈ ગઈ ટાટા ગ્રુપમાં મિસ્ત્રી પરિવારની શેર્સ વેલ્યુ, જૂના સંબંધો અંત ભણી, જાણો કોને શું મળશે, કોણ શું ગુમાવશે?", "90 varshamāṃ bȇ karȏḍamānthī pȏṇābȇ lākha karȏḍa thaī gaī ṭāṭā grupamāṃ mistrī parivāranī śȇrsa vȇlyu, jūnā sambandhȏ anta bhaṇī, jāṇȏ kȏnȇ śuṃ maḷaśȇ, kȏṇa śuṃ gumāvaśȇ?"
+  test "મુંબઈના એક સ્ટોક બ્રોકરે જણાવ્યું કે ટાટા પોતાના શેર બહાર જતા રોકવા માટે SP ગ્રુપ સાથે સમજૂતી કરી શકે છે.", "mumbaīnā ȇka sṭȏka brȏkarȇ jaṇāvyuṃ kȇ ṭāṭā pȏtānā śȇra bahāra jatā rȏkavā māṭȇ SP grupa sāthȇ samajūtī karī śakȇ chȇ."
+  test "કોલકાતા નાઈટ રાઈડર્સનો ઓફ સ્પિનર સુનીલ નારાયણ વિવાદમાં ફસાઈ ગયો છે", "kȏlakātā nāīṭa rāīḍarsanȏ ȏpha spinara sunīla nārāyaṇa vivādamāṃ phasāī gayȏ chȇ"
+  test "ટાટા અને મિસ્ત્રી પરિવાર વચ્ચે શેર્સની આપ-લે થાય એ માટે કોઈ પારસી વ્યક્તિને મધ્યસ્થી બનાવી શકાય છે અને આ માટે રતન ટાટા પણ પ્રયત્નો કરી શકે છે", "ṭāṭā anȇ mistrī parivāra vaccȇ śȇrsanī āpa-lȇ thāya ȇ māṭȇ kȏī pārasī vyaktinȇ madhyasthī banāvī śakāya chȇ anȇ ā māṭȇ ratana ṭāṭā paṇa prayatnȏ karī śakȇ chȇ"
+  test "મેદાની અમ્પાયરોએ પંજાબ વિરુદ્ધની મેચમાં તેની બોલિંગ એક્શન બાબતે શંકા વ્યક્ત કરી હતી. ફરિયાદ પછી હવે નારાયણને વોર્નિંગ લિસ્ટમાં નાખી દેવાયો છે", "mȇdānī ampāyarȏȇ pañjāba viruddhanī mȇcamāṃ tȇnī bȏliṅga ȇkśana bābatȇ śaṅkā vyakta karī hatī. phariyāda pachī havȇ nārāyaṇanȇ vȏrniṅga lisṭamāṃ nākhī dȇvāyȏ chȇ"
+  test "મોદી સરકારના આત્મનિર્ભર ભારત અભિયાનને સફળતા, પાંચ મહિનામાં ચીન સાથેની વેપાર ખાધ અડધી થઈ ગઈ, ચાઈનિઝ સ્માર્ટફોનની હિસ્સેદારી પણ ઘટી", "mȏdī sarakāranā ātmanirbhara bhārata abhiyānanȇ saphaḷatā, pāñca mahināmāṃ cīna sāthȇnī vȇpāra khādha aḍadhī thaī gaī, cāīnijha smārṭaphȏnanī hissȇdārī paṇa ghaṭī"
+}
+
+dependency "alalc-guj-Gujr-Latn-1997", as: gujrlatn
+
+stage {
+
+  run map.gujrlatn.stage.main
+
+}
+

data/maps/alalc-hin-Deva-Latn-1997.imp

@@ -0,0 +1,248 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:hin
+  source_script: Deva
+  destination_script: Latn
+  name: Hindi Romanization, 1997
+  url: http://catdir.loc.gov/catdir/cpso/romanization/hindi.pdf
+  creation_date: 1997
+  description: |
+    ALA-LC Romanization table for Hindi
+
+  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.
+
+    - Anunāsika before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
+      labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
+
+    - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+}
+
+tests {
+  test "हम", "hama"
+  test "मीन", "mīna"
+  test "औसत", "ăusata"
+  test "माँऽऽऽ!", "mān̐’’’!"
+  test "माँ", "mām̐"
+  test "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर", "gaṃbhīr marījoṃ ke māmale meṃ bhārat dūsare naṃbar para"
+  test "कोरोना अपडेट्स", "koronā apaḍeṭsa"
+  test "सीडीसी चीफ का बयान अहम", "sīḍīsī cīph kā bayān ahama"
+  test "गूगल प्ले स्टोर पर पेटीएम की वापसी", "gūgal ple sṭor par peṭīem kī vāpasī"
+  test "भारत में गैंबलिंग की इजाजत नहीं", "bhārat meṃ gaiṃbaliṃg kī ijājat nahīṃ"
+  test "कोरोना वैक्सीन मुद्दे पर घिरे राष्ट्रपति; जो बाइडेन बोले- मुझे और देश को वैज्ञानिकों पर भरोसा है, डोनाल्ड ट्रम्प पर नहीं", "koronā vaiksīn mudde par ghire rāshṭrapati; jo bāiḍen bole- mujhe ăur deś ko vaijñānikoṃ par bharosā hai, ḍonālḍ ṭramp par nahīṃ"
+  test "गूगल की कार्रवाई पर पेटीएम ने कहा था कि ऐप को अस्थायी तौर पर प्ले-स्टोर से हटाया गया है, आपके पैसे सुरक्षित हैं", "gūgal kī kārravāī par peṭīem ne kahā thā ki aip ko asthāyī tăur par ple-sṭor se haṭāyā gayā hai, āpake paise surakshit haiṃ"
+  test "२५६८७५४४६४४६१६११", "2568754464461611"
+}
+
+aliases {
+  def_alias hin_cons_or_conscluster, any("\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d")
+}
+
+stage {
+
+  # RULES
+  # note[2]
+  sub capture("क" + maybe("=")), "k", after: hin_cons_or_conscluster
+  sub capture("क़" + maybe("=")), "q", after: hin_cons_or_conscluster
+  sub capture("ख" + maybe("=")), "kh", after: hin_cons_or_conscluster
+  sub capture("ख़" + maybe("=")), "kh", after: hin_cons_or_conscluster
+  sub capture("ग" + maybe("=")), "g", after: hin_cons_or_conscluster
+  sub capture("ग़" + maybe("=")), "gh", after: hin_cons_or_conscluster
+  sub capture("घ" + maybe("=")), "gh", after: hin_cons_or_conscluster
+  sub capture("ङ" + maybe("=")), "ṅ", after: hin_cons_or_conscluster
+  sub capture("च" + maybe("=")), "c", after: hin_cons_or_conscluster
+  sub capture("छ" + maybe("=")), "ch", after: hin_cons_or_conscluster
+  sub capture("ज" + maybe("=")), "j", after: hin_cons_or_conscluster
+  sub capture("ज़" + maybe("=")), "j", after: hin_cons_or_conscluster
+  sub capture("झ" + maybe("=")), "jh", after: hin_cons_or_conscluster
+  sub capture("ञ" + maybe("=")), "ñ", after: hin_cons_or_conscluster
+  sub capture("ट" + maybe("=")), "ṭ", after: hin_cons_or_conscluster
+  sub capture("ट़" + maybe("=")), "t̤", after: hin_cons_or_conscluster
+  sub capture("ठ" + maybe("=")), "ṭh", after: hin_cons_or_conscluster
+  sub capture("ड" + maybe("=")), "ḍ", after: hin_cons_or_conscluster
+  sub capture("ड़" + maybe("=")), "ṛ", after: hin_cons_or_conscluster
+  sub capture("ड़" + maybe("=")), "ṛ", after: hin_cons_or_conscluster
+  sub capture("ढ" + maybe("=")), "ḍh", after: hin_cons_or_conscluster
+  sub capture("ढ़" + maybe("=")), "ṛh", after: hin_cons_or_conscluster
+  sub capture("ण" + maybe("=")), "ṇ", after: hin_cons_or_conscluster
+  sub capture("त" + maybe("=")), "t", after: hin_cons_or_conscluster
+  sub capture("थ" + maybe("=")), "th", after: hin_cons_or_conscluster
+  sub capture("द" + maybe("=")), "d", after: hin_cons_or_conscluster
+  sub capture("ध" + maybe("=")), "dh", after: hin_cons_or_conscluster
+  sub capture("न" + maybe("=")), "n", after: hin_cons_or_conscluster
+  sub capture("प" + maybe("=")), "p", after: hin_cons_or_conscluster
+  sub capture("फ" + maybe("=")), "ph", after: hin_cons_or_conscluster
+  sub capture("फ़" + maybe("=")), "ph", after: hin_cons_or_conscluster
+  sub capture("ब" + maybe("=")), "b", after: hin_cons_or_conscluster
+  sub capture("भ" + maybe("=")), "bh", after: hin_cons_or_conscluster
+  sub capture("म" + maybe("=")), "m", after: hin_cons_or_conscluster
+  sub capture("य" + maybe("=")), "y", after: hin_cons_or_conscluster
+  sub capture("र" + maybe("=")), "r", after: hin_cons_or_conscluster
+  sub capture("ल" + maybe("=")), "l", after: hin_cons_or_conscluster
+  sub capture("व" + maybe("=")), "v", after: hin_cons_or_conscluster
+  sub capture("श" + maybe("=")), "ś", after: hin_cons_or_conscluster
+  sub capture("ष" + maybe("=")), "sh", after: hin_cons_or_conscluster
+  sub capture("स" + maybe("=")), "s", after: hin_cons_or_conscluster
+  sub capture("स़" + maybe("=")), "s̤", after: hin_cons_or_conscluster
+  sub capture("ह" + maybe("=")), "h", after: hin_cons_or_conscluster
+  sub capture("ह़" + maybe("=")), "h", after: hin_cons_or_conscluster
+
+  # note[3]
+  sub "\u0902", "ṅ", after: any("कक़खख़गग़घङ")
+  sub "\u0902", "ñ", after: any("चछजज़झञ")
+  sub "\u0902", "ṇ", after: any("टट़ठडड़ढढ़ण")
+  sub "\u0902", "n", after: any("तथदधन")
+  # note[4]
+  sub "\u0901", "m̐", after: boundary, before: ""
+
+
+  # CHARACTERS
+  parallel {
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    sub "अ", "a"
+    sub "आ", "ā"
+    sub "इ", "i"
+    sub "ई", "ī"
+    sub "उ", "u"
+    sub "ऊ", "ū"
+    sub "ऋ", "ṛ"
+    sub "ॠ", "ṝ"
+    sub "ऌ", "ḷ"
+    sub "ॳ", "ĕ"
+    sub "ए", "e"
+    sub "ॲ", "ê"
+    sub "अै", "ăi"
+    sub "ऐ", "ai"
+    sub "ऒ", "ŏ"
+    sub "ओ", "o"
+    sub "ऑ", "ô"
+    sub "औ", "ău"
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "क", "ka"
+    sub "क़", "qa"
+    sub "ख", "kha"
+    sub "ख़", "kha"
+    sub "ग", "ga"
+    sub "ग़", "gha"
+    sub "घ", "gha"
+    sub "ङ", "ṅa"
+
+    # Palatals
+    sub "च", "ca"
+    sub "छ", "cha"
+    sub "ज", "ja"
+    sub "ज़", "ja"
+    sub "झ", "jha"
+    sub "ञ", "ña"
+
+    # Cerebrals
+    sub "ट", "ṭa"
+    sub "ट़", "t̤a"
+    sub "ठ", "ṭha"
+    sub "ड", "ḍa"
+    sub "ड़", "ṛa"
+    sub "ड़", "ṛa"
+    sub "ढ", "ḍha"
+    sub "ढ़", "ṛha"
+    sub "ण", "ṇa"
+
+    # Dentals
+    sub "त", "ta"
+    sub "थ", "tha"
+    sub "द", "da"
+    sub "ध", "dha"
+    sub "न", "na"
+
+    # Labials
+    sub "प", "pa"
+    sub "फ", "pha"
+    sub "फ़", "pha"
+    sub "ब", "ba"
+    sub "भ", "bha"
+    sub "म", "ma"
+
+    # Semivowels
+    sub "य", "ya"
+    sub "र", "ra"
+    sub "ल", "la"
+    sub "व", "va"
+
+    # Sibilants
+    sub "श", "śa"
+    sub "ष", "sha"
+    sub "स", "sa"
+    sub "स़", "s̤a"
+
+    # Aspirate
+    sub "ह", "ha"
+    sub "ह़", "ha"
+
+    # Anusvāra
+    sub "ं", "ṃ"
+
+    # Bisarga
+    sub "ः ", "ḥ"
+
+    # Anunāsika
+    sub "ँ", "n̐" # ঁ : n̐, m̐
+
+    # Abagraha
+    sub "ऽ", "’" # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    sub "ा", "ā"
+    sub "ॉ", "ô"
+    sub "ि", "i"
+    sub "ी", "ī"
+    sub "ु", "u"
+    sub "ू", "ū"
+    sub "ृ", "ṛ"
+    sub "ॄ", "ṝ"
+    sub "े", "e"
+    sub "ॊ", "ŏ"
+    sub "ौ", "ău"
+    sub "ै", "ai"
+    sub "ो", "o"
+    sub "्", ""
+    sub "़", ""
+
+    # digits
+
+    sub "०", "0"
+    sub "१", "1"
+    sub "२", "2"
+    sub "३", "3"
+    sub "४", "4"
+    sub "५", "5"
+    sub "६", "6"
+    sub "७", "7"
+    sub "८", "8"
+    sub "९", "9"
+  }
+  compose
+}

data/maps/alalc-hin-Deva-Latn-2011.imp

@@ -0,0 +1,63 @@
+metadata {
+  authority_id: alalc
+  id: 2011
+  language: iso-639-2:hin
+  source_script: Deva
+  destination_script: Latn
+  name: Hindi Romanization, 2011
+  url: https://www.loc.gov/catdir/cpso/romanization/hindi.pdf
+  creation_date: 1997
+  description: |
+    ALA-LC Romanization table for Hindi
+
+  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.
+
+    - Anunāsika before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
+      labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
+
+    - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+}
+
+tests {
+  test "इस चुनौतीपूर्ण समय में 'वर्क फ्रॉम होम’ सामान्य बन चुका है", "is cunăutīpūrṇ samay meṃ 'vark phrôm homa’ sāmāny ban cukā hai"
+  test "दिल्ली में त्योहार पर खरीददारी करने निकले बड़ी संख्या में लोग, कई जगहों पर लगा भीषण जाम", "dillī meṃ tyohār par kharīdadārī karane nikale baṛī saṃkhyā meṃ loga, kaī jagahoṃ par lagā bhīshaṇ jāma"
+  test "सरकार ने पेंशन भोगियों को लाइफ सर्टिफिकेट जमा कराने के मामले में दी बड़ी राहत", "sarakār ne peṃśan bhogiyoṃ ko lāiph sarṭiphikeṭ jamā karāne ke māmale meṃ dī baṛī rāhata"
+  test "कांग्रेस ने माना उसके लचर प्रदर्शन ने डुबोई महागठबंधन की लुटिया, पार्टी में उठने लगी आत्ममंथन की आवाज", "kāṃgres ne mānā usake lacar pradarśan ne ḍuboī mahāgaṭhabandhan kī luṭiyā, pārṭī meṃ uṭhane lagī ātmamanthan kī āvāja"
+  test "डिजिटल पेमेंट सिस्टम ने छोटे-मध्यम कारोबारों का दिया साथ, कोरोना की परेशानियों को किया कम", "ḍijiṭal pemeṃṭ sisṭam ne choṭe-madhyam kārobāroṃ kā diyā sātha, koronā kī pareśāniyoṃ ko kiyā kama"
+  test "छोटे व्यापारियों को ढूंढें, उनसे खरीदें और उनका साथ दें", "choṭe vyāpāriyoṃ ko ḍhūṃḍheṃ, unase kharīdeṃ ăur unakā sāth deṃ"
+  test "भारत के साथ साझीदारी को महत्व देंगे बाइडन, ओबामा प्रशासन में रहीं वरिष्ठ अधिकारी एलिसा ने जताई उम्मीद", "bhārat ke sāth sājhīdārī ko mahatv deṃge bāiḍana, obāmā praśāsan meṃ rahīṃ varishṭh adhikārī elisā ne jatāī ummīda"
+  test "दो महीने से कोमा में था युवक, चिकन की चर्चा सुनते ही आया होश", "do mahīne se komā meṃ thā yuvaka, cikan kī carcā sunate hī āyā hośa"
+  test "कोरोना के टीके पर खुशखबरी, भारत पहुंची रूसी वैक्सीन की पहली खेप", "koronā ke ṭīke par khuśakhabarī, bhārat pahuṃcī rūsī vaiksīn kī pahalī khepa"
+  test "दिल्ली के गांधी नगर स्थित एक दुकान में लगी भीषण आग, दमकल की 20 गाड़ियां मौके पर", "dillī ke gāṃdhī nagar sthit ek dukān meṃ lagī bhīshaṇ āga, damakal kī 20 gāṛiyāṃ măuke para"
+}
+
+
+dependency "alalc-hin-Deva-Latn-1997", as: devalatn
+
+stage {
+
+  run map.devalatn.stage.main
+
+}
+

data/maps/alalc-kan-Kana-Latn-1997.imp

@@ -0,0 +1,233 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:kan
+  source_script: Kana
+  destination_script: Latn
+  name: Kannada Romanization, 1997
+  url: http://catdir.loc.gov/catdir/cpso/romanization/kannada.pdf
+  creation_date: 1997
+  description: |
+    ALA-LC Romanization table for Kannada
+
+  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 superscript sign (◌್).
+
+    - |
+      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 {
+  test "ಕರ್ಣಾಟಕ", "karṇāṭaka"
+  test "ಬೆಂಗಳೂರು", "beṅgaḷūru"
+  test "ಉಡುಪಿಯಲ್ಲಿ ಪ್ರಪ್ರಥಮ ಬಾರಿಗೆ ಪ್ರಾರಂಭವಾಗಿರುವ ದೇಶಿ ಉತ್ಪನ್ನಗಳ ಮಳಿಗೆ", "uḍupiyalli praprathama bārige prāraṃbhavāgiruva dēśi utpannagaḷa maḷige"
+  test "ದೇವರ ಹೆಸರು ಬಳಸಿ ಆನ್‌ಲೈನ್‌ ಬೆಟ್ಟಿಂಗ್‌!", "dēvara hesaru baḷasi ānlain beṭṭiṃg!"
+  test "ಚಿಕ್ಕಮಗಳೂರು : ಪುಷ್ಪ ಸಮರ್ಪಣೆ ವೇಳೆ ಮಗಳನ್ನ ನೆನೆದು ಕಣ್ಣೀರಿಟ್ಟ ಮೃತ ಪೇದೆ ತಾಯಿ", "cikkamagaḷūru : puṣpa samarpaṇe vēḷe magaḷanna nenedu kaṇṇīriṭṭa mṛta pēde tāyi"
+  test "ಸ್ವಾಮಿತ್ವ: ಹೊಸ ಯೋಜನೆಯಿಂದ ನಮಗೆ ಏನು ಲಾಭ ?", "svāmitva: hosa yōjaneyinda namage ēnu lābha ?"
+  test "ಮರಳು ಸಾಗಾಣಿಕೆ ವ್ಯವಹಾರ ಆಗಬಾರದು :ಅಧಿಕಾರಿಗಳಿಗೆ ಖಡಕ್ ಸೂಚನೆ ನೀಡಿದ ಜಿಲ್ಲಾಧಿಕಾರಿ", "maraḷu sāgāṇike vyavahāra āgabāradu :adhikārigaḷige khaḍak sūcane nīḍida jillādhikāri"
+  test "ಹಾವೇರಿ ಜಿಲ್ಲೆಯಲ್ಲಿ ೯೭ ಜನರಲ್ಲಿ ಕೋವಿಡ್ ಸೋಂಕು ಪತ್ತೆ ; 54 ಮಂದಿ ಗುಣಮುಖ", "hāvēri jilleyalli 97 janaralli kōviḍ sōṃku patte ; 54 maṃdi guṇamukha"
+  test "ಸಿಂದಗಿ ಐಸಿಐಸಿಐ ಬ್ಯಾಂಕ್ ಸೆಕ್ಯುರಿಟಿ ಗಾರ್ಡ್ ಹತ್ಯೆ ಪ್ರಕರಣ ಭೇದಿಸಿದ ಪೊಲೀಸರು", "sindagi aisiaisiai byāṃk sekyuriṭi gārḍ hatye prakaraṇa bhēdisida polīsaru"
+  test "ಬ್ಯಾಂಕರ್‌ಗಳೊಂದಿಗೆ ಡಿವಿ ಸಭೆ : ಆಧ್ಯತಾ ವಲಯ, ಸಾಲ ಯೋಜನೆ ತ್ವರಿತ ಮಂಜೂರಿಗೆ ಸೂಚನೆ", "byāṅkargaḷoṃdige ḍivi sabhe : ādhyatā valaya, sāla yōjane tvarita maṃjūrige sūcane"
+  test "ಪೊಲೀಸ್‌ ಇಲಾಖೆ ಸಮಗ್ರ ಅಭಿವೃದ್ಧಿ; ಡಿಜಿಪಿ ನೇತೃತ್ವದಲ್ಲಿ ಸಮಿತಿ ರಚನೆ: ಬೊಮ್ಮಾಯಿ", "polīs ilākhe samagra abhivṛddhi; ḍijipi nētṛtvadalli samiti racane: beūmmāyi"
+  test "ಕೆಟ್ಟಿರುವ ರಸ್ತೆಗಳ ದುರಸ್ತಿಗೆ ಸರಕಾರದ ಯೋಜನೆ", "keṭṭiruva rastegaḷa durastige sarakārada yōjane"
+}
+
+aliases {
+  def_alias kana_chars_1, any("\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd")
+}
+
+stage {
+
+  # RULES
+  # to cover diacritic and vowel less consonants rule II
+    sub "ಕ", "k", after: kana_chars_1
+    sub "ಖ", "kh", after: kana_chars_1
+    sub "ಗ", "g", after: kana_chars_1
+    sub "ಘ", "gh", after: kana_chars_1
+    sub "ಙ", "ṅ", after: kana_chars_1
+    sub "ಚ", "c", after: kana_chars_1
+    sub "ಛ", "ch", after: kana_chars_1
+    sub "ಜ", "j", after: kana_chars_1
+    sub "ಝ", "jh", after: kana_chars_1
+    sub "ಞ", "ñ", after: kana_chars_1
+    sub "ಟ", "ṭ", after: kana_chars_1
+    sub "ಠ", "ṭh", after: kana_chars_1
+    sub "ಡ", "ḍ", after: kana_chars_1
+    sub "ಢ", "ḍh", after: kana_chars_1
+    sub "ಣ", "ṇ", after: kana_chars_1
+    sub "ತ", "t", after: kana_chars_1
+    sub "ಥ", "th", after: kana_chars_1
+    sub "ದ", "d", after: kana_chars_1
+    sub "ಧ", "dh", after: kana_chars_1
+    sub "ನ", "n", after: kana_chars_1
+    sub "ಪ", "p", after: kana_chars_1
+    sub "ಫ", "ph", after: kana_chars_1
+    sub "ಬ", "b", after: kana_chars_1
+    sub "ಭ", "bh", after: kana_chars_1
+    sub "ಮ", "m", after: kana_chars_1
+    sub "ಯ", "y", after: kana_chars_1
+    sub "ರ", "r", after: kana_chars_1
+    sub "ಱ", "ṟ", after: kana_chars_1
+    sub "ಲ", "l", after: kana_chars_1
+    sub "ಳ", "ḷ", after: kana_chars_1
+    sub "ೞ", "l̤", after: kana_chars_1
+    sub "ವ", "v", after: kana_chars_1
+    sub "ಶ", "ś", after: kana_chars_1
+    sub "ಷ", "ṣ", after: kana_chars_1
+    sub "ಸ", "s", after: kana_chars_1
+    sub "ಹ", "h", after: kana_chars_1
+
+  # rule[III]
+    sub "\u0C82", "ṅ", after: any("ಕಖಗಘಙ")
+    sub "\u0C82", "ñ", after: any("ಚಛಜಝಞ")
+    sub "\u0C82", "ṇ", after: any("ಟಠಡಢಣ")
+    sub "\u0C82", "n", after: any("ತಥದಧನ")
+
+
+  # CHARACTERS
+  parallel {
+    sub "ಅ", "a"
+    sub "ಆ", "ā"
+    sub "ಇ", "i"
+    sub "ಈ", "ī"
+    sub "ಉ", "u"
+    sub "ಊ", "ū"
+    sub "ಋ", "ṛ"
+    sub "ೠ", "ṝ"
+
+    sub "ಌ", "ḻ"
+
+    sub "ಎ", "e"
+    sub "ಏ", "ē"
+    sub "ಐ", "ai"
+
+    sub "ಒ", "o"
+    sub "ಓ", "ō"
+    sub "ಔ", "au"
+
+    # Gutturals
+    sub "ಕ", "ka"
+    sub "ಖ", "kha"
+    sub "ಗ", "ga"
+    sub "ಘ", "gha"
+    sub "ಙ", "ṅa"
+
+    # Palatals
+    sub "ಚ", "ca"
+    sub "ಛ", "cha"
+    sub "ಜ", "ja"
+    sub "ಝ", "jha"
+    sub "ಞ", "ña"
+
+    # Cerebrals
+    sub "ಟ", "ṭa"
+    sub "ಠ", "ṭha"
+    sub "ಡ", "ḍa"
+    sub "ಢ", "ḍha"
+    sub "ಣ", "ṇa"
+
+    # Dentals
+    sub "ತ", "ta"
+    sub "ಥ", "tha"
+    sub "ದ", "da"
+    sub "ಧ", "dha"
+    sub "ನ", "na"
+
+    # Labials
+    sub "ಪ", "pa"
+    sub "ಫ", "pha"
+    sub "ಬ", "ba"
+    sub "ಭ", "bha"
+    sub "ಮ", "ma"
+
+    # Semivowels
+    sub "ಯ", "ya"
+    sub "ರ", "ra"
+    sub "ಱ", "ṟa"
+    sub "ಲ", "la"
+    sub "ಳ", "ḷa"
+    sub "ೞ", "l̤a"
+
+
+    sub "ವ", "va"
+
+    # Sibilants
+    sub "ಶ", "śa"
+    sub "ಷ", "ṣa"
+    sub "ಸ", "sa"
+
+
+    # Aspirate
+    sub "ಹ", "ha"
+
+
+    # Bisarga
+    sub "ಃ", "ḥ"
+
+    # Anusvāra
+    sub "ಂ", "ṃ"
+
+    sub "\u0cbc", "" #nukta
+
+    # Medials # Needed for connecting constants
+    sub "ಾ", "ā"
+    sub "ಿ", "i"
+    sub "ೀ", "ī"
+    sub "ು", "u"
+    sub "ೂ", "ū"
+    sub "ೃ", "ṛ"
+    sub "ೄ", "ṝ"
+    sub "\u0CE2", "ḻ" # KANNADA VOWEL SIGN VOCALIC L ( ೢ)
+
+
+    sub "ೆ", "e"
+    sub "ೇ", "ē"
+    sub "ೈ", "ai"
+
+
+    sub "ೊ", "o"
+    sub "ೋ", "ō"
+    sub "ೌ", "au"
+
+
+    sub "्", ""
+    sub "़", ""
+    sub "್", "" # used for pronounciation without vowel
+    sub "‍", "" # no need for zero with joiner
+    sub "‌", "" # no need for zero with non joiner
+
+
+
+    # Digits
+
+    sub "೦", "0"
+    sub "೧", "1"
+    sub "೨", "2"
+    sub "೩", "3"
+    sub "೪", "4"
+    sub "೫", "5"
+    sub "೬", "6"
+    sub "೭", "7"
+    sub "೮", "8"
+    sub "೯", "9"
+  }
+
+  compose
+}
+