interscript 0.1.6 → 0.1.7

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

@@ -0,0 +1,64 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:guj
+source_script: Gujr
+destination_script: Latn
+name: Gujarati Romanization, 2011
+alias:
+  ogc11122:
+    code: guj_Gujr2Latn_ALA_2011
+    description: Gujarati ALA-Library of Congress 2011 System
+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:
+  - source: "મોર્ગન અને રસેલ ફ્લોપ રહ્યા"
+    expected: "mȏrgana anȇ rasȇla phlȏpa rahyā"
+  - source: "રોયલ ચેલેન્જર્સ બેંગલોરના કેપ્ટન વિરાટ કોહલીએ કોલકાતા નાઈટ રાઈડર્સ સામે શારજાહ ખાતે ટોસ જીતીને બેટિંગ લીધી છે."
+    expected: "rȏyala cȇlȇnjarsa bȇṅgalȏranā kȇpṭana virāṭa kȏhalīȇ kȏlakātā nāīṭa rāīḍarsa sāmȇ śārajāha khātȇ ṭȏsa jītīnȇ bȇṭiṅga līdhī chȇ."
+  - source: "અમદાવાદમાં ભણી ચૂકેલા શ્રીકાંત દાતાર પ્રતિષ્ઠિત હાર્વર્ડ બિઝનેસ સ્કૂલના ડીન બન્યા"
+    expected: "amadāvādamāṃ bhaṇī cūkȇlā śrīkānta dātāra pratishṭhita hārvarḍa bijhanȇsa skūlanā ḍīna banyā"
+  - source: "ઓગસ્ટ મહિનામાં મેન્યુફેક્ચરિંગ સેક્ટરનું ઉત્પાદન ગગડ્યુ"
+    expected: "ȏgasṭa mahināmāṃ mȇnyuphȇkcariṅga sȇkṭaranuṃ utpādana gagaḍyu"
+  - source: "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?"
+    expected: "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?"
+  - source: "મુંબઈના એક સ્ટોક બ્રોકરે જણાવ્યું કે ટાટા પોતાના શેર બહાર જતા રોકવા માટે SP ગ્રુપ સાથે સમજૂતી કરી શકે છે."
+    expected: "mumbaīnā ȇka sṭȏka brȏkarȇ jaṇāvyuṃ kȇ ṭāṭā pȏtānā śȇra bahāra jatā rȏkavā māṭȇ SP grupa sāthȇ samajūtī karī śakȇ chȇ."
+  - source: "કોલકાતા નાઈટ રાઈડર્સનો ઓફ સ્પિનર સુનીલ નારાયણ વિવાદમાં ફસાઈ ગયો છે"
+    expected: "kȏlakātā nāīṭa rāīḍarsanȏ ȏpha spinara sunīla nārāyaṇa vivādamāṃ phasāī gayȏ chȇ"
+  - source: "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"
+    expected: "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"
+  - source: "મેદાની અમ્પાયરોએ પંજાબ વિરુદ્ધની મેચમાં તેની બોલિંગ એક્શન બાબતે શંકા વ્યક્ત કરી હતી. ફરિયાદ પછી હવે નારાયણને વોર્નિંગ લિસ્ટમાં નાખી દેવાયો છે"
+    expected: "mȇdānī ampāyarȏȇ pañjāba viruddhanī mȇcamāṃ tȇnī bȏliṅga ȇkśana bābatȇ śaṅkā vyakta karī hatī. phariyāda pachī havȇ nārāyaṇanȇ vȏrniṅga lisṭamāṃ nākhī dȇvāyȏ chȇ"
+  - source: "મોદી સરકારના આત્મનિર્ભર ભારત અભિયાનને સફળતા, પાંચ મહિનામાં ચીન સાથેની વેપાર ખાધ અડધી થઈ ગઈ, ચાઈનિઝ સ્માર્ટફોનની હિસ્સેદારી પણ ઘટી"
+    expected: "mȏdī sarakāranā ātmanirbhara bhārata abhiyānanȇ saphaḷatā, pāñca mahināmāṃ cīna sāthȇnī vȇpāra khādha aḍadhī thaī gaī, cāīnijha smārṭaphȏnanī hissȇdārī paṇa ghaṭī"
+
+map:
+
+  inherit: 'alalc-guj-Gujr-Latn-1997'

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

@@ -0,0 +1,211 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:hin
+source_script: Deva
+destination_script: Latn
+name: Hindi Romanization, 1997
+alias:
+  ogc11122:
+    code: hin_Deva2Latn_ALA_1997
+    description: Hindi ALA-Library of Congress 1997 System
+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:
+  - source: "हम"
+    expected: "hama"
+  - source: "मीन"
+    expected: "maīna"
+  - source: "औसत"
+    expected: "ăusata"
+  - source: "माँऽऽऽ!"
+    expected: "maān̐’’’!"
+  - source: "माँ"
+    expected: "maām̐"
+  - source: "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर"
+    expected: "gaṃbhaīra maraījaoṃ kae maāmalae maeṃ bhaārata daūsarae naṃbara para"
+  - source: "कोरोना अपडेट्स"
+    expected: "kaoraonaā apaḍaeṭasa"
+  - source: "सीडीसी चीफ का बयान अहम"
+    expected: "saīḍaīsaī caīpha kaā bayaāna ahama"
+  - source: "गूगल प्ले स्टोर पर पेटीएम की वापसी"
+    expected: "gaūgala palae saṭaora para paeṭaīema kaī vaāpasaī"
+  - source: "भारत में गैंबलिंग की इजाजत नहीं"
+    expected: "bhaārata maeṃ gaaiṃbalaiṅga kaī ijaājata nahaīṃ"
+  - source: "कोरोना वैक्सीन मुद्दे पर घिरे राष्ट्रपति; जो बाइडेन बोले- मुझे और देश को वैज्ञानिकों पर भरोसा है, डोनाल्ड ट्रम्प पर नहीं"
+    expected: "kaoraonaā vaaikasaīna maudadae para ghairae raāshaṭarapatai; jao baāiḍaena baolae- maujhae ăura daeśa kao vaaijañaānaikaoṃ para bharaosaā haai, ḍaonaālaḍa ṭaramapa para nahaīṃ"
+  - source: "गूगल की कार्रवाई पर पेटीएम ने कहा था कि ऐप को अस्थायी तौर पर प्ले-स्टोर से हटाया गया है, आपके पैसे सुरक्षित हैं"
+    expected: "gaūgala kaī kaāraravaāī para paeṭaīema nae kahaā thaā kai aipa kao asathaāyaī taăura para palae-saṭaora sae haṭaāyaā gayaā haai, āpakae paaisae saurakashaita haaiṃ"
+  - source: "२५६८७५४४६४४६१६११"
+    expected: "2568754464461611"
+
+map:
+
+  rules:
+    # note[3]
+    - pattern: \u0902(?=[कक़खख़गग़घङ])
+      result: ṅ
+    - pattern: \u0902(?=[चछजज़झञ])
+      result: ñ
+    - pattern: \u0902(?=[टट़ठडड़ढढ़ण])
+      result: ṇ
+    - pattern: \u0902(?=[तथदधन])
+      result: n
+    # note[4]
+    - pattern: (?<=)\u0901(?=\b)
+      result: "m̐"
+
+  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': 'ḷ'
+    'ॳ': 'ĕ'
+    'ए': 'e'
+    'ॲ': 'ê'
+    'अै': 'ăi'
+    'ऐ': 'ai'
+    'ऒ': 'ŏ'
+    'ओ': 'o'
+    'ऑ': 'ô'
+    'औ': 'ău'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'ka'
+    'क़': 'qa'
+    'ख': 'kha'
+    'ख़': 'kha'
+    'ग': 'ga'
+    'ग़': 'gha'
+    'घ': 'gha'
+    'ङ': 'ṅa'
+
+    # Palatals
+    'च': 'ca'
+    'छ': 'cha'
+    'ज': 'ja'
+    'ज़': 'ja'
+    'झ': 'jha'
+    'ञ': 'ña'
+
+    # Cerebrals
+    'ट': 'ṭa'
+    'ट़': 't̤a'
+    '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'
+    'फ़': 'pha'
+    'ब': 'ba'
+    'भ': 'bha'
+    'म': 'ma'
+
+    # Semivowels
+    'य': 'ya'
+    'र': 'ra'
+    'ल': 'la'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'śa'
+    'ष': 'sha'
+    'स': 'sa'
+    'स़': 's̤a'
+
+    # Aspirate
+    'ह': 'ha'
+    'ह़': 'ha'
+
+    # Anusvāra
+    'ं': 'ṃ'
+
+    # Bisarga
+    'ः ': 'ḥ'
+
+    # Anunāsika
+    'ँ': 'n̐' # ঁ : n̐, m̐
+
+    # Abagraha
+    'ऽ': '’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ॉ': "ô"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛ"
+    'ॄ': "ṝ"
+    'े': "e"
+    'ॊ': "ŏ"
+    'ौ': "ău"
+    'ै': "ai"
+    'ो': "o"
+    '्': ""
+
+    # digits
+
+    '०': '0'
+    '१': '1'
+    '२': '2'
+    '३': '3'
+    '४': '4'
+    '५': '5'
+    '६': '6'
+    '७': '7'
+    '८': '8'
+    '९': '9'

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

@@ -0,0 +1,47 @@
+---
+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:
+  - source: "इस चुनौतीपूर्ण समय में 'वर्क फ्रॉम होम’ सामान्य बन चुका है"
+    expected: "isa caunaăutaīpaūraṇa samaya maeṃ 'varaka pharaôma haoma’ saāmaānaya bana caukaā haai"
+
+map:
+
+  inherit: "alalc-hin-Deva-Latn-1997"

data/maps/alalc-kat-Geok-Latn-1997.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: alalc
 id: 1997
-language: kat
+language: iso-639-2:kat
 source_script: Geok
 destination_script: Latn
 name: ALA-LC Georgian System (1997)

data/maps/alalc-kat-Geor-Latn-1997.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: alalc
 id: 1997
-language: kat
+language: iso-639-2:kat
 source_script: Geor
 destination_script: Latn
 name: ALA-LC Georgian System (1997)
+alias:
+  ogc11122:
+    code: kat_Geor2Latn_ALA_1997
+    description: Georgian ALA-Library of Congress 1997 System
 url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
 creation_date: 1997
 confirmation_date: 1997

data/maps/alalc-kor-Hang-Latn-1997.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: alalc
 id: 1997
-language: kor
+language: iso-639-2:kor
 source_script: Hang
 destination_script: Latn
 name: ALA-LC Romanization Table -- Korean (1997)
+alias:
+  ogc11122:
+    code: kor_Hang2Latn_ALA_1997
+    description: Korean ALA-Library of Congress 1997 System
 url: http://catdir.loc.gov/catdir/cpso/romanization/korean.pdf
 creation_date: 1997
 adoption_date:

data/maps/alalc-mal-Mlym-Latn-1997.yaml

@@ -0,0 +1,303 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:mal
+source_script: Mlym
+destination_script: Latn
+name: Malayalam Romanization, 1997
+alias:
+  ogc11122:
+    code: mal_Mlym2Latn_ALA_1997
+    description: Malayalam ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/malayala.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Malayalam
+
+
+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.
+
+  - When  ് is used in combination with the vowel u (ഉ്), the combination is also transliterated ȧ.
+
+  - |
+    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
+    b) when the absence of any vowel is indicated by the superscript sign  ് (also used for the vowel ȧ); and
+    c) when the following modified consonantal forms are used:
+      ൿ  k
+      ൻ  n
+      ൾ  ḷ
+      ൺ  ṇ
+      ൽ  l
+      ർ   r
+  - When റ റ appears as a subscript in a cluster (റ്റ), it is transliterated ta.
+
+  - |
+    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: "ചൈനയ്ക്കെതിരെ ലഡാക്കിൽ സദാസജ്ജം; യുഎസിൽനിന്ന് ൭൨,൫൦൦ സിഗ്–൧൬ റൈഫിൾ"
+    expected: "cainayŭkŭketire lad̂ākŭkil sadāsajŭjaṃ; yuesilninŭnŭ 72,500 sigŭ–16 ṟaiphiḷ"
+  - source: "സർഗഭൂമിക’യ്ക്കില്ല; ലളിതച്ചേച്ചി അങ്ങനെ പറഞ്ഞിട്ടുണ്ടാവില്ല: ആർഎൽവി രാമകൃഷ്ണൻ"
+    expected: "sargabhūmika’yŭkŭkilŭla; laḷitacŭcēcŭci aṅŭṅane paṟañŭñiṭŭṭuṇŭṭāvilŭla: ārelvi rāmakṛṣŭṇan"
+  - source: "സ്വർണക്കടത്ത്‌: ഫൈസൽ ഫരീദും റബിന്‍സും ദുബായിൽ അറസ്റ്റിലായെന്ന്‌ എന്‍ഐഎ"
+    expected: "sŭvarṇakŭkaṭatŭtŭ: phaisal pharīduṃ ṟabinŭsuṃ dubāyil aṟasŭṟŭṟilāyenŭnŭ enŭaie"
+  - source: "വരുമോ ചൈനയുടെ വാക്സീൻ?; ആഗോള ഉപയോഗത്തിന് ഡബ്ല്യുഎച്ച്ഒയുമായി ചർച്ച"
+    expected: "varumō cainayuṭe vākŭsīn?; āgōḷa upayōgatŭtinŭ d̂abŭlŭyuecŭcŭoyumāyi carcŭca"
+  - source: "കുട്ടികളുടെ മാനസിക പിരിമുറുക്കം മാറ്റാൻ പരിശീലനം; ക്ലാസുമായി പോക്സോ പ്രതി"
+    expected: "kuṭŭṭikaḷuṭe mānasika pirimuṟukŭkaṃ māṟŭṟān pariśīlanaṃ; kŭlāsumāyi pōkŭsō pŭrati"
+  - source: "ആദ്യം അമിത് ഷാ, ഇപ്പോൾ മോദി; ബിജെപിയെ പുണരാൻ ജഗൻ; ആന്ധ്രയിലെ കരുനീക്കങ്ങൾ"
+    expected: "ādŭyaṃ amitŭ ṣā, ipŭpōḷ mōdi; bijepiye puṇarān jagan; ānŭdhŭrayile karunīkŭkaṅŭṅaḷ"
+  - source: "ലഹരിമരുന്ന് കേസ്: ബിനീഷ് കോടിയേരിയെ ഇഡി 6 മണിക്കൂർ ചോദ്യം ചെയ്തു"
+    expected: "laharimarunŭnŭ kēsŭ: binīṣŭ kōṭiyēriye id̂i 6 maṇikŭkūr cōdŭyaṃ ceyŭtu"
+  - source: "ഈന്തപ്പഴം വിതരണം ചെയ്തത് ശിവശങ്കര്‍ പറഞ്ഞതു പ്രകാരം: ടി.വി അനുപമയുടെ മൊഴി"
+    expected: "īnŭtapŭpaḻaṃ vitaraṇaṃ ceyŭtatŭ śivaśaṅŭkarŭ paṟañŭñatu pŭrakāraṃ: ṭi.vi anupamayuṭe moḻi"
+  - source: "൫൦൦൦ മണിക്കൂർ കാത്തിരിക്കാൻ തയാറെന്ന് രാഹുൽ: ഒടുവിൽ വഴങ്ങി ഹരിയാന"
+    expected: "5000 maṇikŭkūr kātŭtirikŭkān tayāṟenŭnŭ rāhul: oṭuvil vaḻaṅŭṅi hariyāna"
+  - source: "കാരണം ഷോര്‍ട്ട്‌സര്‍ക്യൂട്ടല്ല; കത്തിയത് ഫയല്‍ മാത്രം, സാനിറ്റൈസര്‍ ഉള്‍പ്പെടെ കത്തിയില്ല"
+    expected: "kāraṇaṃ ṣōrŭṭŭṭŭsarŭkŭyūṭŭṭalŭla; katŭtiyatŭ phayalŭ mātŭraṃ, sāniṟŭṟaisarŭ uḷŭpŭpeṭe katŭtiyilŭla"
+  - source: "വിമൺ സയൻറിസ്റ്റ്സ് സ്കീം"
+    expected: "vimaṇ sayanṟisŭṟŭṟŭsŭ sŭkīṃ"
+
+map:
+
+  rules:
+    # note[5]
+    - pattern: \u0DCA(?=[കഖഗഘങ])
+      result: ṅ
+    - pattern: \u0DCA(?=[ചഛജഝഞ])
+      result: ñ
+    - pattern: \u0DCA(?=[ടഠഡഢണ])
+      result: ṇ
+    - pattern: \u0DCA(?=[തഥദധന])
+      result: n
+
+    # note[3(a,b)]
+    - pattern: (['ക']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'k'
+    - pattern: (['ഖ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'kh'
+    - pattern: (['ഗ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'g'
+    - pattern: (['ഘ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'gh'
+    - pattern: (['ങ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṅ'
+    - pattern: (['ച']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'c'
+    - pattern: (['ഛ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ch'
+    - pattern: (['ജ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'j'
+    - pattern: (['ഝ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'jh'
+    - pattern: (['ഞ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ñ'
+    - pattern: (['ട']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṭ'
+    - pattern: (['ഠ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṭh'
+    - pattern: (['ഡ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'd̂'
+    - pattern: (['ഢ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ḍh'
+    - pattern: (['ണ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṇ'
+    - pattern: (['ത']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 't'
+    - pattern: (['ഥ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'th'
+    - pattern: (['ദ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'd'
+    - pattern: (['ധ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'dh'
+    - pattern: (['ന']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'n'
+    - pattern: (['പ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'p'
+    - pattern: (['ഫ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ph'
+    - pattern: (['ബ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'b'
+    - pattern: (['ഭ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'bh'
+    - pattern: (['മ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'm'
+    - pattern: (['യ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'y'
+    - pattern: (['ര']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'r'
+    - pattern: (['റ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṟ'
+    - pattern: (['ല']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'l'
+    - pattern: (['ള']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ḷ'
+    - pattern: (['ഴ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ḻ'
+    - pattern: (['വ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'v'
+    - pattern: (['ശ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ś'
+    - pattern: (['ഷ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṣ'
+    - pattern: (['സ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 's'
+    - pattern: (['ഩ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṉ'
+    - pattern: (['ഹ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'h'
+    
+
+
+  characters:
+
+    'അ': 'a'
+    'ആ': 'ā'
+    'ഇ': 'i'
+    'ഈ': 'ī'
+    'ഉ': 'u'
+    'ഊ': 'ū'
+    'ഋ': "ṛ"
+    'ൠ': "ṝ"
+    'ഌ': "ḷ"
+    'ൡ': "ḹ"
+
+    'എ': 'e'
+    'ഏ': 'ē'
+    'ഐ': 'ai'
+
+    'ഒ': 'o'
+    'ഓ': 'ō'
+    'ഔ': 'au'
+
+    # Consonants
+    # Gutturals
+    'ക': 'ka'
+    'ഖ': 'kha'
+    'ഗ': 'ga'
+    'ഘ': 'gha'
+    'ങ': 'ṅa'
+
+    # Palatals
+    'ച': 'ca'
+    'ഛ': 'cha'
+    'ജ': 'ja'
+    'ഝ': 'jha'
+    'ഞ': 'ña'
+
+    # Cerebrals
+    'ട':  'ṭa'
+    'ഠ':  'ṭha'
+    'ഡ': 'd̂a'
+    'ഢ':  'ḍha'
+    'ണ':  'ṇa'
+
+    # Dentals
+    'ത': 'ta'
+    'ഥ': 'tha'
+    'ദ': 'da'
+    'ധ': 'dha'
+    'ന': 'na'
+
+    # Labials
+    'പ': 'pa'
+    'ഫ': 'pha'
+    'ബ': 'ba'
+    'ഭ': 'bha'
+    'മ': 'ma'
+
+    # Semivowels
+    'യ': 'ya'
+    'ര': 'ra'
+    'റ': 'ṟa'
+    'റ്റ': 'ṯṯa' # (see Note 4)
+    'ല': 'la'
+    'ള': 'ḷa'
+    'ഴ': 'ḻa'
+    # Sibilants
+    'വ': 'va'
+    'ശ': 'śa'
+    'ഷ': 'ṣa'
+    'സ': 'sa'
+    'ഩ': 'ṉa'
+
+
+    # Aspirate
+    'ഹ': 'ha'
+
+    # Bisarga
+    'ഃ': 'ḥ'
+
+    # Anusvāra
+    'ം': 'ṃ'
+
+
+    # Abagraha
+    'ഽ': ':’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+
+    'ാ': 'ā'
+    'ി': 'i'
+    'ീ': 'ī'
+    'ു': 'u'
+    'ൂ': 'ū'
+    '്': 'ŭ'
+    'ൃ': "ṛ"
+    'ൄ': "ṝ"
+    '\u0D62': "ḷ"
+    '\u0D63': "ḹ"
+    'െ': "e"
+    'േ': "ē"
+    'ൈ': "ai"
+    'ൊ': 'o'
+    'ോ': 'ō'
+    'ൌ': 'au'
+
+    '्': ''
+    '़': ''
+    'ൗ': ''
+    "‍": '' # no need for zero with joiner
+    "‌": '' # no need for zero with non joiner
+
+
+    # numbers
+    '൦': '0'
+    '൧': '1'
+    '൨': '2'
+    '൩': '3'
+    '൪': '4'
+    '൫': '5'
+    '൬': '6'
+    '൭': '7'
+    '൮': '8'
+    '൯': '9'
+    '൰': '10'
+    '൱': '100'
+    '൲': '1000'
+
+
+    # Note 3(c)
+
+    'ൿ': 'k'
+    'ൺ': 'ṇ'
+    'ൻ': 'n'
+    'ൽ': 'l'
+    'ൾ': 'ḷ'
+    'ർ': 'r'
+    'ഉ്': 'ū'
+
+    # extended and ancient forms
+
+    'ഺ': 'ṯa'