interscript-maps 2.0.5

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

@@ -0,0 +1,65 @@
+metadata {
+  authority_id: alalc
+  id: 2012
+  language: iso-639-2:mal
+  source_script: Mlym
+  destination_script: Latn
+  name: Malayalam Romanization, 2012
+  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 {
+  test "ബാർ കോഴ ആവിയായി; മകൻ മാണിയെ വ്യക്തിഹത്യ നടത്തിയവരുടെ കൂടാരത്തിൽ", "bār kōḻa āviyāyi; makan māṇiye vŭyakŭtihatŭya naṭatŭtiyavaruṭe kūṭāratŭtil"
+  test "മിഷൻ ശക്തി, ഓപറേഷൻ ശക്തി'; മുഖം മിനുക്കാൻ സ്ത്രീസുരക്ഷാ പദ്ധതികളുമായി", "miṣan śakŭti, ōpaṟēṣan śakŭti'; mukhaṃ minukŭkān sŭtŭrīsurakŭṣā padŭdhatikaḷumāyi"
+  test "സംസ്ഥാനത്ത് ബുധനാഴ്ച 6,244 പേര്‍ക്ക് കോവിഡ്; ൫൭൪൫ പേര്‍ക്ക് രോഗം സമ", "saṃsŭthānatŭtŭ budhanāḻŭca 6,244 pērŭkŭkŭ kōvid̂ŭ; 5745 pērŭkŭkŭ rēāgaṃ sama"
+  test "ശബരിമല തീര്‍ഥാടനം: സ്‌പെഷല്‍ കമ്മീഷ്ണറുടെ റിപ്പോര്‍ട്ട് ഹൈകോടതിയില്‍", "śabarimala tīrŭthāṭanaṃ: sŭpeṣalŭ kamŭmīṣŭṇaṟuṭe ṟipŭpōrŭṭŭṭŭ haikōṭatiyilŭ"
+  test "സജ്‌ന ഷാജിക്ക് ഐക്യദാര്‍ഢ്യവുമായി സന്തോഷ് കീഴാറ്റൂര്‍ ബിരിയാണി വില്‍ക്കും", "sajŭna ṣājikŭkŭ aikŭyadārŭḍhŭyavumāyi sanŭtōṣŭ kīḻāṟŭṟūrŭ biriyāṇi vilŭkŭkuṃ"
+  test "ആനപ്പുറത്തിരുന്ന് യോഗാഭ്യാസത്തിനിടെ ബാബ രാംദേവ് നിലത്തുവീണു", "ānapŭpuṟatŭtirunŭnŭ yēāgābhŭyāsatŭtiniṭe bāba rāṃdēvŭ nilatŭtuvīṇu"
+  test "സാധാരണക്കാരെൻറ ദീപാവലി നിങ്ങളുടെ കൈയിൽ; മൊറട്ടോറിയം കേസിൽ കേന്ദ്രത്തോട് സുപ്രീംകോടതി", "sādhāraṇakŭkārenṟa dīpāvali niṅŭṅaḷuṭe kaiyil; meāṟaṭŭṭēāṟiyaṃ kēsil kēnŭdŭratŭtēāṭŭ supŭrīṃkēāṭati"
+  test "മാണി ഉണ്ടായിരുന്നെങ്കിൽ ഇത്തരമൊരു തീരുമാനം എടുക്കില്ല, ഈ രാഷ്ട്രീയ വഞ്ചന അദ്ദേഹത്തിന്‍റെ ആത്മാവ് പൊറുക്കില്ല", "māṇi uṇŭṭāyirunŭneṅŭkil itŭtaramoru tīrumānaṃ eṭukŭkilŭla, ī rāṣŭṭŭrīya vañŭcana adŭdēhatŭtinŭṟe ātŭmāvŭ poṟukŭkilŭla"
+  test "ധാർമികത വിളമ്പണ്ട, എം.പി, എം.എൽ.എ സ്ഥാനങ്ങൾ രാജിവെക്കൂ എന്ന് ജോസ് കെ. മാണിയോട് ഷാഫി", "dhārmikata viḷamŭpaṇŭṭa, eṃ.pi, eṃ.el.e sŭthānaṅŭṅaḷ rājivekŭkū enŭnŭ jōsŭ ke. māṇiyōṭŭ ṣāphi"
+  test "ഞങ്ങൾ ബോക്സിൽ നിന്നും ഒന്നും ഒഴിവാക്കില്ല; ആപ്പിളിനെ ട്രോളി ഷവോമി", "ñaṅŭṅaḷ bēākŭsil ninŭnuṃ onŭnuṃ oḻivākŭkilŭla; āpŭpiḷine ṭŭrēāḷi ṣavēāmi"
+}
+
+dependency "alalc-mal-Mlym-Latn-1997", as: mlymlatn
+
+stage {
+
+  run map.mlymlatn.stage.main
+
+}
+

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

@@ -0,0 +1,178 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:mar
+  source_script: Deva
+  destination_script: Latn
+  name: Marathi Romanization, 1997
+  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 {
+  test "ठाणे - जिल्ह्यात बुधवारी एक हजार रुग्णांची वाढ, तर जणांच्या मृत्यूची नोंद", "ṭhaāṇae - jailahayaāta baudhavaāraī eka hajaāra raugaṇaāñcaī vaāḍha, tara jaṇaāñcayaā maṛitayaūcaī naonda"
+  test "एकता कपूर पुन्हा अडकली वादात, वेबसीरिजमधल्या 'त्या' सीनमुळे जमावाची घरावर दगडफेक", "ekataā kapaūra paunahaā aḍakalaī vaādaāta, vaebasaīraijamadhalayaā 'tayaā' saīnamaulae jamaāvaācaī gharaāvara dagaḍaphaeka"
+  test "जाणून घ्या, बीएमसीच्या अधिकाऱ्यांनी कंगना राणौतच्या ऑफिसमधले नक्की काय- काय तोडलं", "jaāṇaūna ghayaā, baīemasaīcayaā adhaikaāऱyaānnaī kaṅganaā raāṇaautacayaā ôphaisamadhalae nakakaī kaāya- kaāya taoḍalam"
+  test "कंगना मुंबईत दाखल होण्यापूर्वी 'मातोश्री'वरून फर्मान सुटले; प्रवक्त्यांना सक्त आदेश", "kaṅganaā maumbaīta daākhala haoṇayaāpaūravaī 'maātaośaraī'varaūna pharamaāna sauṭalae; paravakatayaānnaā sakata ādaeśa"
+  test "मराठा आरक्षणास तात्पुरती स्थगिती; सर्वोच्च न्यायालयाचा निर्णय", "maraāṭhaā ārakashaṇaāsa taātapaurataī sathagaitaī; saravaocaca nayaāyaālayaācaā nairaṇaya"
+  test "भारताच्या तिन्ही लशींचा पहिला टप्पा यशस्वी, वाचा कधी येणार बाजारात", "bhaārataācayaā tainahaī laśaīñcaā pahailaā ṭapapaā yaśasavaī, vaācaā kadhaī yaeṇaāra baājaāraāta"
+  test "रुग्णवाढीमुळे खाटांची चणचण", "raugaṇavaāḍhaīmaulae khaāṭaāñcaī caṇacaṇa"
+  test "पीएम स्वनिधी कर्ज योजनेला मुंबईतून अल्प प्रतिसाद", "paīema savanaidhaī karaja yaojanaelaā maumbaītaūna alapa parataisaāda"
+  test "सांताक्रूझ-चेंबूर लिंक रोडवरील उन्नत मार्गाला स्थगिती", "saāntaākaraūjha-caembaūra laiṅka raoḍavaraīla unanata maāragaālaā sathagaitaī"
+  test "संपादक अर्णब गोस्वामी यांच्याविरूद्ध खडक पोलिस ठाण्यात तक्रार", "sampaādaka araṇaba gaosavaāmaī yaāñcayaāvairaūdadha khaḍaka paolaisa ṭhaāṇayaāta takaraāra"
+  test "२५६८७५४४६४४६१६११", "2568754464461611"
+}
+
+stage {
+
+  # RULES
+  # note[3]
+  sub "\u0902", "ṅ", after: any("कखगघङ")
+  sub "\u0902", "ñ", after: any("चछजझञ")
+  sub "\u0902", "ṇ", after: any("टठडढण")
+  sub "\u0902", "n", after: any("तथदधन")
+
+
+  # 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", "ḹ"
+    #'ॳ': 'ĕ'
+    sub "ए", "e"
+    sub "ॲ", "ê"
+    #'अै': 'ai'
+    sub "ऐ", "ai"
+    #'ऒ': 'ŏ'
+    sub "ओ", "o"
+    sub "ऑ", "ô"
+    sub "औ", "ău"
+
+    # II. Consonants
+    # Gutturals
+    sub "क", "ka"
+    sub "ख", "kha"
+    sub "ग", "ga"
+    sub "घ", "gha"
+    sub "ङ", "ṅa"
+
+    # Palatals
+    sub "च", "ca"
+    sub "छ", "cha"
+    sub "ज", "ja"
+    sub "झ", "jha"
+    sub "ञ", "ña"
+
+    # Cerebrals
+    sub "ट", "ṭa"
+    sub "ठ", "ṭha"
+    sub "ड", "ḍa"
+    #'ड़': 'ṛa'
+    sub "ढ", "ḍha"
+    #'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 "ब", "ba"
+    sub "भ", "bha"
+    sub "म", "ma"
+
+    # Semivowels
+    sub "य", "ya"
+    sub "र", "ra"
+    sub "ल", "la"
+    sub "ळ", "la"
+    sub "व", "va"
+
+    # Sibilants
+    sub "श", "śa"
+    sub "ष", "sha"
+    sub "स", "sa"
+
+    # Aspirate
+    sub "ह", "ha"
+
+    # Anusvāra
+    sub "ं", "m"
+
+    # Bisarga
+    sub "ः ", "ḥ"
+
+    # Abagraha
+    sub "ऽ", "’" # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    sub "ा", "ā"
+    sub "ि", "i"
+    sub "ी", "ī"
+    sub "ु", "u"
+    sub "ू", "ū"
+    sub "ृ", "ṛi"
+    sub "ॄ", "rī"
+    sub "े", "e"
+    sub "ो", "o"
+    sub "ौ", "au"
+    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-mar-Deva-Latn-2011.imp

@@ -0,0 +1,51 @@
+metadata {
+  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 {
+  test "कोरोनाच्या लढाईत पोलीस थकलेत, पण हिंमत हरलेले नाहीत; गृहमंत्र्यांकडून कौतुक", "kaoraonaācayaā laḍhaāīta paolaīsa thakalaeta, paṇa haimmata haralaelae naāhaīta; gaṛihamantarayaāṅkaḍaūna kaautauka"
+}
+
+dependency "alalc-mar-Deva-Latn-1997", as: devalatn
+
+stage {
+
+  run map.devalatn.stage.main
+
+}
+

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

@@ -0,0 +1,125 @@
+metadata {
+  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 {
+  test "Општина Ердут", "Opština Erdut"
+  test "Општина Двор", "Opština Dvor"
+  test "ЛУЃЕ луѓе", "LUǴE luǵe"
+  test "ЅВЕЗДА ѕвезда Ѕвезда", "DZVEZDA dzvezda Dzvezda"
+  test "ЌАРУВАЊЕ ќарување", "ḰARUVANJE ḱaruvanje"
+}
+
+dependency "posix", import: true
+
+stage {
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A"
+    sub "Б", "B"
+    sub "В", "V"
+    sub "Г", "G"
+    sub "Ѓ", "Ǵ" # Ǵ
+    sub "Д", "D"
+    sub "Ђ", "Đ" # Đ
+    sub "Е", "E"
+    sub "Ж", "Ž" # Ž
+    sub "З", "Z"
+    sub "Ѕ", "Dz"
+    sub "И", "I"
+    sub "Ј", "J"
+    sub "К", "K"
+    sub "Ќ", "Ḱ" # Ḱ
+    sub "Л", "L"
+    sub "Љ", "Lj"
+    sub "М", "M"
+    sub "Н", "N"
+    sub "Њ", "Nj"
+    sub "О", "O"
+    sub "П", "P"
+    sub "Р", "R"
+    sub "С", "S"
+    sub "Т", "T"
+    sub "Ћ", "Ć" # Ć
+    sub "У", "U"
+    sub "Ф", "F"
+    sub "Х", "H"
+    sub "Ц", "C"
+    sub "Ч", "Č" # Č
+    sub "Џ", "Dž" # Dž
+    sub "Ш", "Š" # Š
+    sub "а", "a"
+    sub "б", "b"
+    sub "в", "v"
+    sub "г", "g"
+    sub "ѓ", "ǵ" # ǵ
+    sub "д", "d"
+    sub "ђ", "đ" # đ
+    sub "е", "e"
+    sub "ж", "ž" # ž
+    sub "з", "z"
+    sub "ѕ", "dz"
+    sub "и", "i"
+    sub "ј", "j"
+    sub "к", "k"
+    sub "ќ", "ḱ" # ḱ
+    sub "л", "l"
+    sub "љ", "lj"
+    sub "м", "m"
+    sub "н", "n"
+    sub "њ", "nj"
+    sub "о", "o"
+    sub "п", "p"
+    sub "р", "r"
+    sub "с", "s"
+    sub "т", "t"
+    sub "ћ", "ć" # ć
+    sub "у", "u"
+    sub "ф", "f"
+    sub "х", "h"
+    sub "ц", "c"
+    sub "ч", "č" # č
+    sub "џ", "dž" # dž
+    sub "ш", "š" # š
+  }
+
+  # POSTRULES
+  # rewritten by hand to work properly
+  # DZ
+  sub capture(maybe(upper)) + "Dz" + capture(upper), ref(1) + "DZ" + ref(2)
+  sub capture(upper) + "Dz" +  capture(maybe(upper)), ref(1) + "DZ" + ref(2)
+
+  #LJ
+  sub capture(upper) + "Lj" + capture(maybe(upper)), ref(1) + "LJ" + ref(2)
+  sub capture(maybe(upper)) + "Lj" + capture(upper), ref(1) + "LJ" + ref(2)
+
+  #NJ
+  sub capture(upper) + "Nj" + capture(maybe(upper)), ref(1) + "NJ" + ref(2)
+  sub capture(maybe(upper)) + "Nj" + capture(upper), ref(1) + "NJ" + ref(2)
+
+  #DŽ
+  sub capture(upper) + "Dž" + capture(maybe(upper)), ref(1) + "DŽ" + ref(2)
+  sub capture(maybe(upper)) + "Dž" + capture(upper), ref(1) + "DŽ" + ref(2)
+
+  compose
+}
+

data/maps/alalc-mkd-Cyrl-Latn-2013.imp

@@ -0,0 +1,113 @@
+metadata {
+  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 {
+  test "Општина Ердут", "Opština Erdut"
+  test "Општина Двор", "Opština Dvor"
+  test "ЛУЃЕ луѓе", "LUǴE luǵe"
+  test "ЅВЕЗДА ѕвезда Ѕвезда", "DZVEZDA dzvezda Dzvezda"
+  test "ЌАРУВАЊЕ ќарување", "ḰARUVANJE ḱaruvanje"
+}
+
+dependency "posix", import: true
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A"
+    sub "Б", "B"
+    sub "В", "V"
+    sub "Г", "G"
+    sub "Ѓ", "Ǵ" # Ǵ
+    sub "Д", "D"
+    sub "Ђ", "Đ" # Đ
+    sub "Е", "E"
+    sub "Ж", "Ž" # Ž
+    sub "З", "Z"
+    sub "Ѕ", "Dz"
+    sub "И", "I"
+    sub "Ј", "J"
+    sub "К", "K"
+    sub "Ќ", "Ḱ" # Ḱ
+    sub "Л", "L"
+    sub "Љ", "Lj"
+    sub "М", "M"
+    sub "Н", "N"
+    sub "Њ", "Nj"
+    sub "О", "O"
+    sub "П", "P"
+    sub "Р", "R"
+    sub "С", "S"
+    sub "Т", "T"
+    sub "У", "U"
+    sub "Ф", "F"
+    sub "Х", "H"
+    sub "Ц", "C"
+    sub "Ч", "Č" # Č
+    sub "Џ", "Dž" # Dž
+    sub "Ш", "Š" # Š
+    sub "а", "a"
+    sub "б", "b"
+    sub "в", "v"
+    sub "г", "g"
+    sub "ѓ", "ǵ" # ǵ
+    sub "д", "d"
+    sub "ђ", "đ" # đ
+    sub "е", "e"
+    sub "ж", "ž" # ž
+    sub "з", "z"
+    sub "ѕ", "dz"
+    sub "и", "i"
+    sub "ј", "j"
+    sub "к", "k"
+    sub "ќ", "ḱ" # ḱ
+    sub "л", "l"
+    sub "љ", "lj"
+    sub "м", "m"
+    sub "н", "n"
+    sub "њ", "nj"
+    sub "о", "o"
+    sub "п", "p"
+    sub "р", "r"
+    sub "с", "s"
+    sub "т", "t"
+    sub "у", "u"
+    sub "ф", "f"
+    sub "х", "h"
+    sub "ц", "c"
+    sub "ч", "č" # č
+    sub "џ", "dž" # dž
+    sub "ш", "š" # š
+  }
+
+  # POSTRULES
+  # rewritten by hand to work properly
+  # DZ
+  sub capture(maybe(upper)) + "Dz" + capture(upper), ref(1) + "DZ" + ref(2)
+  sub capture(upper) + "Dz" +  capture(maybe(upper)), ref(1) + "DZ" + ref(2)
+
+  #LJ
+  sub capture(upper) + "Lj" + capture(maybe(upper)), ref(1) + "LJ" + ref(2)
+  sub capture(maybe(upper)) + "Lj" + capture(upper), ref(1) + "LJ" + ref(2)
+
+  #NJ
+  sub capture(upper) + "Nj" + capture(maybe(upper)), ref(1) + "NJ" + ref(2)
+  sub capture(maybe(upper)) + "Nj" + capture(upper), ref(1) + "NJ" + ref(2)
+
+  #DŽ
+  sub capture(upper) + "Dž" + capture(maybe(upper)), ref(1) + "DŽ" + ref(2)
+  sub capture(maybe(upper)) + "Dž" + capture(upper), ref(1) + "DŽ" + ref(2)
+
+  compose
+}
+