interscript 0.1.3 → 0.1.9

data/maps/bis-dev-Deva-Latn-13194-1991.yaml

@@ -0,0 +1,184 @@
+---
+authority_id: bis
+id: 1991
+language: iso-639-2:dev
+source_script: Deva
+destination_script: Latn
+name: Indian script code for information interchange - ISCII - Devanagri 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: "हम"
+    expected: "hm"
+  - source: "मीन"
+    expected: "mīn"
+  - source: "औसत"
+    expected: "aust"
+  - source: "माँ"
+    expected: "mām"
+  - source: "ट्रंप बोले, चीन को देश बेच देगा बिडेन परिवार, वैक्सीन लाने की कोशिशों में अड़ंगा डालने का लगाया आरोप"
+    expected: "ṭrmp bōlē, cīn kō dēś bēc dēgā biḍēn privār, vaiksīn lānē kī kōśiśōṃ mēṃ aḍṅgā ḍālnē kā lgāyā ārōp"
+  - source: "चालबाज चीन से तनातनी के बीच पश्चिमी मोर्चे को लगातार मजबूत कर रही वायुसेना"
+    expected: "cālbāj cīn sē tnātnī kē bīc pścimī mōrcē kō lgātār mjbūt kr rhī vāyusēnā"
+  - source: "चीन ने पांचों भारतीय नागरिकों को रिहा किया, PLA ने किया था अगवा"
+    expected: "cīn nē pāñcōṃ bhārtīy nāgrikōṃ kō rihā kiyā, PLA nē kiyā thā agvā"
+  - source: "पूर्व नौसेना अधिकारी मदन शर्मा से रक्षा मंत्री राजनाथ सिंह ने की बात, कहा- ऐसे हमले हैं अस्वीकार्य"
+    expected: "pūrv nausēnā adhikārī mdn śrmā sē rkṣā mntrī rājnāth siṃh nē kī bāt, khā- aisē hmlē haiṃ asvīkāry"
+  - source: "सात दिन बाद ही छोड़ दिया ससुराल"
+    expected: "sāt din bād hī chōd̂ diyā ssurāl"
+  - source: "राजस्‍थान में फि‍र खींचतान, पायलट ने गहलोत को लिखा पत्र, याद दिलाया घोषणा-पत्र, कहा- नाखुश है गुर्जर समाज"
+    expected: "rājsthān mēṃ phir khīñctān, pāylṭ nē ghlōt kō likhā ptr, yād dilāyā ghōṣṇā-ptr, khā- nākhuś hai gurjr smāj"
+
+map:
+
+  rules:
+    # note
+    - pattern: \u0902(?=[कखगघङ])
+      result: ṅ
+    - pattern: \u0902(?=[चछजझञ])
+      result: ñ
+    - pattern: \u0902(?=[टठडढण])
+      result: ṇ
+    - pattern: \u0902(?=[तथदधन])
+      result: n
+    - pattern: \u0902(?=[पफबभम])
+      result: m
+
+
+  characters:
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ऋ': 'ṛ'
+    'ॠ': 'ṝ'
+    'ऌ': 'ḻ'
+    'ॡ': 'ḹ'
+
+    'ए': 'ē'
+    'ऐ': 'ai'
+    'ऍ': 'ê'
+
+    'ऒ': 'o'
+    'ओ': 'ŏ'
+    'औ': 'au'
+    'ऑ': 'ô'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'k'
+    'ख': 'kh'
+    'ग': 'g'
+    'घ': 'gh'
+    'ङ': 'ṅ'
+
+    # Palatals
+    'च': 'c'
+    'छ': 'ch'
+    'ज': 'j'
+    'झ': 'jh'
+    'ञ': 'ñ'
+
+    # Cerebrals
+    'ट': 'ṭ'
+    'ठ': 'ṭh'
+    'ड': 'ḍ'
+    'ढ': 'ḍh'
+    'ण': 'ṇ'
+
+    # Dentals
+    'त': 't'
+    'थ': 'th'
+    'द': 'd'
+    'ध': 'dh'
+    'न': 'n'
+    'ऩ': 'ṉ'
+
+    # Labials
+    'प': 'p'
+    'फ': 'ph'
+    'ब': 'b'
+    'भ': 'bh'
+    'म': 'm'
+
+    # Semivowels
+    'य': 'y'
+    'य़': 'ẏ'
+    'र': 'r'
+    'ऱ': 'ṟ'
+    'ल': 'l'
+    'ळ': 'ḷ'
+    'ऴ': 'ẕ'
+
+
+    'व': 'v'
+
+    # Sibilants
+    'श': 'ś'
+    'ष': 'ṣ'
+    'स': 's'
+
+
+    # Aspirate
+    'ह': 'h'
+
+
+    #Nukta Constants
+
+    'क़': 'q'
+    'ख़': 'ḵẖ'
+    'ग़': 'gẖ'
+    'ज़': 'z'
+    'ड़': 'd̂'
+    'ढ़': 'd̂h'
+    'फ़': 'f'
+
+    # Chandrabindu
+    'ँ': 'm'
+
+    # Bisarga
+    'ः ': 'ḥ'
+
+    # Anusvāra
+    'ं': 'ṃ'
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛ"
+
+
+    'ॆ': "e"
+    'े': "ē"
+    'ै': "ai"
+    'ॅ': "ê"
+
+
+    'ॊ': 'o'
+    'ो': 'ō'
+    'ौ': 'au'
+    'ॉ': 'ô'
+    '्': ''
+    '़': ''
+    '।': '.'
+    "‍": '' # no need for zero with joiner

data/maps/bis-guj-Gujr-Latn-13194-1991.yaml

@@ -0,0 +1,181 @@
+---
+authority_id: bis
+id: 1991
+language: iso-639-2:guj
+source_script: Gujr
+destination_script: Latn
+name: Indian script code for information interchange - ISCII - Gujrati 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: "અમિત શાહનો કોરોના રિપોર્ટ 2 ઓગસ્ટે પોઝિટિવ આવ્યો હતો, ત્યારથી તેમનું સ્વાસ્થ્ય સારું નથી"
+    expected: "amit śāhnŏ kŏrŏnā ripŏrṭ 2 ŏgsṭē pŏjhiṭiv āvyŏ htŏ, tyārthī tēmnuṃ svāsthy sāruṃ nthī"
+  - source: "મેદાંતા હોસ્પિટલમાં તેમનો ઇલાજ ચાલી રહ્યો હતો"
+    expected: "mēdāntā hŏspiṭlmāṃ tēmnŏ ilāj cālī rhyŏ htŏ"
+  - source: "ભારતના વિશ્વનાથન આનંદે શેનયાનમાં પહેલો ફિડે શતરંજ વિશ્વ કપ જીત્યો"
+    expected: "bhārtnā viśvnāthn ānndē śēnyānmāṃ phēlŏ phiḍē śtrñj viśv kp jītyŏ"
+  - source: "ભારતીય વડા પ્રધાન જવાહરલાલ નેહરુએ 40 લાખ હિન્દુઓ અને મુસલમાનોના પારસ્પરિક સ્થાનાંતરણનું સૂચન આપ્યું"
+    expected: "bhārtīy vḍā prdhān jvāhrlāl nēhruē 40 lākh hinduŏ anē muslmānŏnā pārsprik sthānāntrṇnuṃ sūcn āpyuṃ"
+  - source: "લિબિયાના એલ અજિજિયામાં ધરતી પર સૌથી વધુ તાપમાન નોંધાયું. એ વખતે છાયામાં નોંધવામાં આવેલું તાપમાન 58 ડિગ્રી સેલ્સિયસ હતું."
+    expected: "libiyānā ēl ajijiyāmāṃ dhrtī pr sauthī vdhu tāpmān nŏndhāyuṃ. ē vkhtē chāyāmāṃ nŏndhvāmāṃ āvēluṃ tāpmān 58 ḍigrī sēlsiys htuṃ."
+  - source: "પ્રથમ વિશ્વયુદ્ધઃ જર્મની અને ફ્રાન્સ વચ્ચે એસ્નેની લડાઈ શરૂ થઈ હતી"
+    expected: "prthm viśvyuddhḥ jrmnī anē phrāns vccē ēsnēnī lḍāī śrū thī htī"
+  - source: "એન્ગ્લો-મિસ્ત્ર યુદ્ધઃ તેલ અલ કેબિરનું યુદ્ધ લડવામાં આવ્યું હતું."
+    expected: "ēnglŏ-mistr yuddhḥ tēl al kēbirnuṃ yuddh lḍvāmāṃ āvyuṃ htuṃ."
+  - source: "પુરાવા ન હતા, એ જ કારણે કેસ ચાલ્યો નહીં, પણ તેમને નજરકેદ રાખવામાં આવ્યા"
+    expected: "purāvā n htā, ē j kārṇē kēs cālyŏ nhīṃ, pṇ tēmnē njrkēd rākhvāmāṃ āvyā"
+  - source: "સરદાર પટેલે નક્કી કર્યું હતું કે કાશ્મીર ભારતનો હિસ્સો બનશે; 91 વર્ષ પહેલાં લાહોર જેલમાં ભૂખહડતાળ દરમિયાન શહીદ થયા હતા જતીન દાસ"
+    expected: "srdār pṭēlē nkkī kryuṃ htuṃ kē kāśmīr bhārtnŏ hissŏ bnśē; 91 vrṣ phēlāṃ lāhŏr jēlmāṃ bhūkhhḍtāḷ drmiyān śhīd thyā htā jtīn dās"
+  - source: "કોરોના પ્રોટોકોલ વચ્ચે આજે મેડિકલ પ્રવેશ પરીક્ષા લેવાશેઃ એન્ટ્રી ટચ ફ્રી રહેશે, એડમિટ કાર્ડ બાર કોડથી ચેક થશે"
+    expected: "kŏrŏnā prŏṭŏkŏl vccē ājē mēḍikl prvēś prīkṣā lēvāśēḥ ēnṭrī ṭc phrī rhēśē, ēḍmiṭ kārḍ bār kŏḍthī cēk thśē"
+  - source: "૮૪૬૬૫૪૧૬૪૬૫૧"
+    expected: "846654164651"
+
+
+
+map:
+
+  rules:
+    # note
+    - pattern: \u0A82(?=[કખગઘઙ])
+      result: ṅ
+    - pattern: \u0A82(?=[ચછજઝઞ])
+      result: ñ
+    - pattern: \u0A82(?=[ટઠડઢણ])
+      result: ṇ
+    - pattern: \u0A82(?=[તથદધન])
+      result: n
+    - pattern: \u0A82(?=[પફબભમ])
+      result: m
+
+
+  characters:
+    'અ': 'a'
+    'આ': 'ā'
+    'ઇ': 'i'
+    'ઈ': 'ī'
+    'ઉ': 'u'
+    'ઊ': 'ū'
+   # 'ઋ': 'ṛ'
+    'ઌ': 'ḻ'
+
+    'ઍ': 'e'
+    'એ': 'ē'
+    'ઐ': 'ai'
+
+    'ઑ': 'o'
+    'ઓ': 'ŏ'
+    'ઔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ક': 'k'
+    'ખ': 'kh'
+    'ગ': 'g'
+    'ઘ': 'gh'
+    'ઙ': 'ṅ'
+
+    # Palatals
+    'ચ': 'c'
+    'છ': 'ch'
+    'જ': 'j'
+    'ઝ': 'jh'
+    'ઞ': 'ñ'
+
+    # Cerebrals
+    'ટ':  'ṭ'
+    'ઠ':  'ṭh'
+    'ડ':  'ḍ'
+    'ઢ':  'ḍh'
+    'ણ':  'ṇ'
+
+    # Dentals
+    'ત': 't'
+    'થ': 'th'
+    'દ': 'd'
+    'ધ': 'dh'
+    'ન': 'n'
+
+    # Labials
+    'પ': 'p'
+    'ફ': 'ph'
+    'બ': 'b'
+    'ભ': 'bh'
+    'મ': 'm'
+
+    # Semivowels
+    'ય': 'y'
+    'ર': 'r'
+    'લ': 'l'
+    'ળ': 'ḷ'
+    'વ': 'v'
+
+    # Sibilants
+    'શ': 'ś'
+    'ષ': 'ṣ'
+    'સ': 's'
+
+
+    # Aspirate
+    'હ': 'h'
+
+    # Chandrabindu
+    'ઁ': 'm'
+
+    # Bisarga
+    'ઃ': 'ḥ'
+
+    # Anusvāra
+    'ં': 'ṃ'
+
+    # Medials # Needed for connecting constants
+
+    'ા': 'ā'
+    'િ': 'i'
+    'ી': 'ī'
+    'ુ': 'u'
+    'ૂ': 'ū'
+    'ૃ': 'ṛ'
+    #'ૄ': 'ṛr'
+    'ૅ': 'e'
+    'ે': 'ē'
+    'ૈ': 'ai'
+    'ૉ': 'o'
+    'ો': 'ŏ'
+    'ૌ': 'au'
+
+
+
+    '\u09CD': '' # Used for joining
+    '્': ''
+    '઼': ''
+    '।': '.'
+    "‍": ''# Used for joining
+
+    # digits
+
+    '૦': '0'
+    '૧': '1'
+    '૨': '2'
+    '૩': '3'
+    '૪': '4'
+    '૫': '5'
+    '૬': '6'
+    '૭': '7'
+    '૮': '8'
+    '૯': '9'

data/maps/bis-kan-Kana-Latn-13194-1991.yaml

@@ -0,0 +1,173 @@
+---
+authority_id: bis
+id: 1991
+language: iso-639-2:kan
+source_script: Kana
+destination_script: Latn
+name: Indian script code for information interchange - ISCII - Kannada 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: "ಈಗ ವೈರಲ್ ಆಗುತ್ತಿದೆ ಕಂಗನಾ ರಣಾವುತ್ ಹಳೇಯ ವಿಡಿಯೋ"
+    expected: "īg vairl āguttide kṅgnā rṇāvut hḷēy viḍiyō"
+  - source: "ಸಂಕಷ್ಟ ಎದುರಾದರೆ ಬಿಎಸ್‌ವೈ ಬೆನ್ನಿಗೆ ಎಚ್‌ಡಿಕೆ ?"
+    expected: "sṅkṣṭ edurādre biesvai bennige ecḍike ?"
+  - source: "ಶಾಸಕರಿಂದಲೂ ಒತ್ತಡ?"
+    expected: "śāskrindlū ottḍ?"
+  - source: "ಏಕೆಂದರೆ, ಇವರ ಹೆಸರೇ ಕೊರೊನಾ!"
+    expected: "ēkendre, ivr hesrē keūronā!"
+  - source: "ಕೊರೊನಾಕ್ಕಿಂತಲೂ ಮುಂಚೆಯೇ ಅವರು ಕೊರೊನಾ ಆಗಿದ್ದವರು!"
+    expected: "keūronākkintlū muñceyē avru keūronā āgiddvru!"
+  - source: "ಕೇರಳದ ಕೊಟ್ಟಾಯಂನ ಮಹಿಳೆಯೊಬ್ಬರು ಈಗ ತಮ್ಮ ಹೆಸರು ಹೇಳಲು ಮುಜುಗರ ಪಡುವಂತಾಗಿದೆ"
+    expected: "kērḷd keūṭṭāynn mhiḷeyobbru īg tmm hesru hēḷlu mujugr pḍuvntāgide"
+  - source: "ಬೇರೆ ಬೆಳವಣಿಗೆಗೆ ಸಾಕ್ಷಿ ಸಾಧ್ಯತೆ"
+    expected: "bēre beḷvṇigege sākṣi sādhyte"
+  - source: "ಗುರು ಶನಿ ಗ್ರಹಗಳ ನಡುವೆ 3 ಜನರ ಪ್ರಯಾಣ"
+    expected: "guru śni grhgḷ nḍuve 3 jnr pryāṇ"
+  - source: "ಕೊರೊನಾ ಬಿಕ್ಕಟ್ಟಿನ ಕಾಲದಲ್ಲಿ “ಮಿಸೆಸ್‌ ಕೊರೊನಾ’ಗೆ ಸಮಸ್ಯೆ!"
+    expected: "keūronā bikkṭṭin kāldlli “mises keūronā’ge smsye!"
+  - source: "ಕೆಲವು ತಿಂಗಳಿಂದ ರಷ್ಯಾ ದೇಶದ ಏನಾಟೊಲಿ ಇವ್ಯಾನಿಶಿನ್‌ ಮತ್ತು ಇವಾನ್‌ ವ್ಯಾಗನರ್‌ ಹಾಗೂ ಅಮೆರಿಕಾದ ಕ್ರಿಸ್‌ ಕ್ಯಾಸಿಡಿ ಈ ಉಪಗ್ರಹದಲ್ಲಿ ವಾಸಿಸುತ್ತಿದ್ದಾರೆ"
+    expected: "kelvu tiṅgḷind rṣyā dēśd ēnāṭeūli ivyāniśin mttu ivān vyāgnr hāgū amerikād kris kyāsiḍi ī upgrhdlli vāsisuttiddāre"
+
+
+map:
+
+  rules:
+    # note
+    - pattern: \u0C82(?=[ಕಖಗಘಙ])
+      result: ṅ
+    - pattern: \u0C82(?=[ಚಛಜಝಞ])
+      result: ñ
+    - pattern: \u0C82(?=[ಟಠಡಢಣ])
+      result: ṇ
+    - pattern: \u0C82(?=[ತಥದಧನ])
+      result: n
+    - pattern: \u0C82(?=[ಪಫಬಭಮ])
+      result: m
+
+  characters:
+    'ಅ': 'a'
+    'ಆ': 'ā'
+    'ಇ': 'i'
+    'ಈ': 'ī'
+    'ಉ': 'u'
+    'ಊ': 'ū'
+    'ಋ': 'ṛ'
+    'ಌ': 'ḻ'
+
+    'ಎ': 'e'
+    'ಏ': 'ē'
+    'ಐ': 'ai'
+
+    'ಒ': 'o'
+    'ಓ': 'ŏ'
+    'ಔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ಕ': 'k'
+    'ಖ': 'kh'
+    'ಗ': 'g'
+    'ಘ': 'gh'
+    'ಙ': 'ṅ'
+
+    # Palatals
+    'ಚ': 'c'
+    'ಛ': 'ch'
+    'ಜ': 'j'
+    'ಝ': 'jh'
+    'ಞ': 'ñ'
+
+    # Cerebrals
+    'ಟ': 'ṭ'
+    'ಠ': 'ṭh'
+    'ಡ': 'ḍ'
+    'ಢ': 'ḍh'
+    'ಣ': 'ṇ'
+
+    # Dentals
+    'ತ': 't'
+    'ಥ': 'th'
+    'ದ': 'd'
+    'ಧ': 'dh'
+    'ನ': 'n'
+
+    # Labials
+    'ಪ': 'p'
+    'ಫ': 'ph'
+    'ಬ': 'b'
+    'ಭ': 'bh'
+    'ಮ': 'm'
+
+    # Semivowels
+    'ಯ': 'y'
+    'ರ': 'r'
+    'ಱ': 'ṟ'
+    'ಲ': 'l'
+    'ಳ': 'ḷ'
+ #   'ऴ': 'ẕ'
+
+
+    'ವ': 'v'
+
+    # Sibilants
+    'ಶ': 'ś'
+    'ಷ': 'ṣ'
+    'ಸ': 's'
+
+
+    # Aspirate
+    'ಹ': 'h'
+
+
+    # Chandrabindu
+    '\u0C80': 'm'
+    '\u0C81': 'm'
+
+    # Bisarga
+    'ಃ': 'ḥ'
+
+    # Anusvāra
+    'ಂ': 'ṃ'
+
+    '$಼': '' #nukta
+
+    # Medials # Needed for connecting constants
+    'ಾ': "ā"
+    'ಿ': "i"
+    'ೀ': "ī"
+    'ು': "u"
+    'ೂ': "ū"
+    'ೃ': "ṛ"
+    'ೄ': "ṛr"
+
+
+    'ೆ': "e"
+    'ೇ': "ē"
+    'ೈ': "ai"
+
+
+    'ೊ': 'o'
+    'ೋ': 'ō'
+    'ೌ': 'au'
+
+    '्': ''
+    '़': ''
+    '್': ''
+    "‍": '' # no need for zero with joiner
+    "‌": '' # no need for zero with non joiner