interscript 0.1.2 → 0.1.7

data/maps/alalc-mal-Mlym-Latn-2012.yaml

@@ -0,0 +1,73 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:mal
+source_script: Mlym
+destination_script: Latn
+name: Malayalam Romanization, 2012
+alias:
+  ogc11122:
+    code: mal_Mlym2Latn_ALA_2012
+    description: Malayalam ALA-Library of Congress 2012 System
+url: https://www.loc.gov/catdir/cpso/romanization/malayalam.pdf
+creation_date: 2012
+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: "ബാർ കോഴ ആവിയായി; മകൻ മാണിയെ വ്യക്തിഹത്യ നടത്തിയവരുടെ കൂടാരത്തിൽ"
+    expected: "bār kōḻa āviyāyi; makan māṇiye vŭyakŭtihatŭya naṭatŭtiyavaruṭe kūṭāratŭtil"
+  - source: "മിഷൻ ശക്തി, ഓപറേഷൻ ശക്തി'; മുഖം മിനുക്കാൻ സ്ത്രീസുരക്ഷാ പദ്ധതികളുമായി"
+    expected: "miṣan śakŭti, ōpaṟēṣan śakŭti'; mukhaṃ minukŭkān sŭtŭrīsurakŭṣā padŭdhatikaḷumāyi"
+  - source: "സംസ്ഥാനത്ത് ബുധനാഴ്ച 6,244 പേര്‍ക്ക് കോവിഡ്; ൫൭൪൫ പേര്‍ക്ക് രോഗം സമ"
+    expected: "saṃsŭthānatŭtŭ budhanāḻŭca 6,244 pērŭkŭkŭ kōvid̂ŭ; 5745 pērŭkŭkŭ rēāgaṃ sama"
+  - source: "ശബരിമല തീര്‍ഥാടനം: സ്‌പെഷല്‍ കമ്മീഷ്ണറുടെ റിപ്പോര്‍ട്ട് ഹൈകോടതിയില്‍"
+    expected: "śabarimala tīrŭthāṭanaṃ: sŭpeṣalŭ kamŭmīṣŭṇaṟuṭe ṟipŭpōrŭṭŭṭŭ haikōṭatiyilŭ"
+  - source: "സജ്‌ന ഷാജിക്ക് ഐക്യദാര്‍ഢ്യവുമായി സന്തോഷ് കീഴാറ്റൂര്‍ ബിരിയാണി വില്‍ക്കും"
+    expected: "sajŭna ṣājikŭkŭ aikŭyadārŭḍhŭyavumāyi sanŭtōṣŭ kīḻāṟŭṟūrŭ biriyāṇi vilŭkŭkuṃ"
+  - source: "ആനപ്പുറത്തിരുന്ന് യോഗാഭ്യാസത്തിനിടെ ബാബ രാംദേവ് നിലത്തുവീണു"
+    expected: "ānapŭpuṟatŭtirunŭnŭ yēāgābhŭyāsatŭtiniṭe bāba rāṃdēvŭ nilatŭtuvīṇu"
+  - source: "സാധാരണക്കാരെൻറ ദീപാവലി നിങ്ങളുടെ കൈയിൽ; മൊറട്ടോറിയം കേസിൽ കേന്ദ്രത്തോട് സുപ്രീംകോടതി"
+    expected: "sādhāraṇakŭkārenṟa dīpāvali niṅŭṅaḷuṭe kaiyil; meāṟaṭŭṭēāṟiyaṃ kēsil kēnŭdŭratŭtēāṭŭ supŭrīṃkēāṭati"
+  - source: "മാണി ഉണ്ടായിരുന്നെങ്കിൽ ഇത്തരമൊരു തീരുമാനം എടുക്കില്ല, ഈ രാഷ്ട്രീയ വഞ്ചന അദ്ദേഹത്തിന്‍റെ ആത്മാവ് പൊറുക്കില്ല"
+    expected: "māṇi uṇŭṭāyirunŭneṅŭkil itŭtaramoru tīrumānaṃ eṭukŭkilŭla, ī rāṣŭṭŭrīya vañŭcana adŭdēhatŭtinŭṟe ātŭmāvŭ poṟukŭkilŭla"
+  - source: "ധാർമികത വിളമ്പണ്ട, എം.പി, എം.എൽ.എ സ്ഥാനങ്ങൾ രാജിവെക്കൂ എന്ന് ജോസ് കെ. മാണിയോട് ഷാഫി"
+    expected: "dhārmikata viḷamŭpaṇŭṭa, eṃ.pi, eṃ.el.e sŭthānaṅŭṅaḷ rājivekŭkū enŭnŭ jōsŭ ke. māṇiyōṭŭ ṣāphi"
+  - source: "ഞങ്ങൾ ബോക്സിൽ നിന്നും ഒന്നും ഒഴിവാക്കില്ല; ആപ്പിളിനെ ട്രോളി ഷവോമി"
+    expected: "ñaṅŭṅaḷ bēākŭsil ninŭnuṃ onŭnuṃ oḻivākŭkilŭla; āpŭpiḷine ṭŭrēāḷi ṣavēāmi"
+
+
+map:
+
+  inherit: 'alalc-mal-Mlym-Latn-1997'

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

@@ -0,0 +1,189 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:mar
+source_script: Deva
+destination_script: Latn
+name: Marathi Romanization, 1997
+alias:
+  ogc11122:
+    code: mar_Deva2Latn_ALA_1997
+    description: Marathi ALA-Library of Congress 1997 System
+url: http://catdir.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"
+  - source: "२५६८७५४४६४४६१६११"
+    expected: "2568754464461611"
+
+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"
+    '्': ''
+
+    # digits
+
+    '०': '0'
+    '१': '1'
+    '२': '2'
+    '३': '3'
+    '४': '4'
+    '५': '5'
+    '६': '6'
+    '७': '7'
+    '८': '8'
+    '९': '9'

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

@@ -0,0 +1,45 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:mar
+source_script: Deva
+destination_script: Latn
+name: Marathi Romanization, 2011
+url: https://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: "कोरोनाच्या लढाईत पोलीस थकलेत, पण हिंमत हरलेले नाहीत; गृहमंत्र्यांकडून कौतुक"
+    expected: "kaoraonaācayaā laḍhaāīta paolaīsa thakalaeta, paṇa haimmata haralaelae naāhaīta; gaṛihamantarayaāṅkaḍaūna kaautauka"
+
+map:
+
+  inherit: "alalc-mar-Deva-Latn-1997"

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

@@ -0,0 +1,114 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2: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: iso-639-2: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