interscript 0.1.2 → 0.1.7

data/maps/iso-kan-Knda-Latn-15919-2001.yaml

@@ -0,0 +1,220 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:kan
+source_script: Knda
+destination_script: Latn
+name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+creation_date: 2001
+adoption_date: 2001
+description: |
+  Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+  maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+  Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+  equipment that they are using, cannot read or write the text
+
+  This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+  independent of the period in which it is or was used.
+
+notes:
+
+  - All transliterations made using this International Standard shall be case-insensitive.
+  - Inherent a with a consonant shall always be transliterated.
+  - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+  - candrabindu shall be transliterated as m̐
+  - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+    with a semivowel, it shall be placed before the semivowel.
+  - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+    Indic punctuation is outside the scope of this International Standard.
+  - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+    independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+    shall be attached to the second vowel.
+  - |
+    A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+    follows.
+     -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+  - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+    script, where the second character has a transliteration in this International Standard, then the first character shall
+    be transliterated in the same way as the second character.
+  - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+    the digraphs ai, au, both Latin vowels should be underscored.
+    Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+    consonant, the transliteration should show word division by a space; but when phonological processes result in two
+    words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+    of the language in question.
+
+
+
+tests:
+  - source: "ಈಗ ವೈರಲ್ ಆಗುತ್ತಿದೆ ಕಂಗನಾ ರಣಾವುತ್ ಹಳೇಯ ವಿಡಿಯೋ"
+    expected: "īga vaairala āgautataidae kaṁganaā raṇaāvauta haḷaēya vaiḍaiyaō"
+  - source: "ಸಂಕಷ್ಟ ಎದುರಾದರೆ ಬಿಎಸ್‌ವೈ ಬೆನ್ನಿಗೆ ಎಚ್‌ಡಿಕೆ ?"
+    expected: "saṁkaṣaṭa edauraādarae baiesavaai baenanaigae ecaḍaikae ?"
+  - source: "ಶಾಸಕರಿಂದಲೂ ಒತ್ತಡ?"
+    expected: "śaāsakaraiṁdalaū otataḍa?"
+  - source: "ಏಕೆಂದರೆ, ಇವರ ಹೆಸರೇ ಕೊರೊನಾ!"
+    expected: "ēkaeṁdarae, ivara haesaraē kaeūraonaā!"
+  - source: "ಕೊರೊನಾಕ್ಕಿಂತಲೂ ಮುಂಚೆಯೇ ಅವರು ಕೊರೊನಾ ಆಗಿದ್ದವರು!"
+    expected: "kaeūraonaākakaiṁtalaū mauṁcaeyaē avarau kaeūraonaā āgaidadavarau!"
+  - source: "ಕೇರಳದ ಕೊಟ್ಟಾಯಂನ ಮಹಿಳೆಯೊಬ್ಬರು ಈಗ ತಮ್ಮ ಹೆಸರು ಹೇಳಲು ಮುಜುಗರ ಪಡುವಂತಾಗಿದೆ"
+    expected: "kaēraḷada kaeūṭaṭaāyaṁna mahaiḷaeyaobabarau īga tamama haesarau haēḷalau maujaugara paḍauvaṁtaāgaidae"
+  - source: "ಬೇರೆ ಬೆಳವಣಿಗೆಗೆ ಸಾಕ್ಷಿ ಸಾಧ್ಯತೆ"
+    expected: "baērae baeḷavaṇaigaegae saākaṣai saādhayatae"
+  - source: "ಗುರು ಶನಿ ಗ್ರಹಗಳ ನಡುವೆ 3 ಜನರ ಪ್ರಯಾಣ"
+    expected: "gaurau śanai garahagaḷa naḍauvae 3 janara parayaāṇa"
+  - source: "ಕೊರೊನಾ ಬಿಕ್ಕಟ್ಟಿನ ಕಾಲದಲ್ಲಿ “ಮಿಸೆಸ್‌ ಕೊರೊನಾ’ಗೆ ಸಮಸ್ಯೆ!"
+    expected: "kaeūraonaā baikakaṭaṭaina kaāladalalai “maisaesa kaeūraonaā’gae samasayae!"
+  - source: "ಕೆಲವು ತಿಂಗಳಿಂದ ರಷ್ಯಾ ದೇಶದ ಏನಾಟೊಲಿ ಇವ್ಯಾನಿಶಿನ್‌ ಮತ್ತು ಇವಾನ್‌ ವ್ಯಾಗನರ್‌ ಹಾಗೂ ಅಮೆರಿಕಾದ ಕ್ರಿಸ್‌ ಕ್ಯಾಸಿಡಿ ಈ ಉಪಗ್ರಹದಲ್ಲಿ ವಾಸಿಸುತ್ತಿದ್ದಾರೆ"
+    expected: "kaelavau taiṁgaḷaiṁda raṣayaā daēśada ēnaāṭaeūlai ivayaānaiśaina matatau ivaāna vayaāganara haāgaū amaeraikaāda karaisa kayaāsaiḍai ī upagarahadalalai vaāsaisautataidadaārae"
+  - source: "ಹಾಂಗ್ ಕಾಂಗ್"
+    expected: "haāṁga kaāṁga"
+  - source: "೧೮೧೪೦"
+    expected: "18140"
+
+
+map:
+
+  characters:
+    'ಅ': 'a'
+    'ಆ': 'ā'
+    'ಇ': 'i'
+    'ಈ': 'ī'
+    'ಉ': 'u'
+    'ಊ': 'ū'
+    'ಋ': 'ṛ'
+    'ೠ': "ṝ"
+    'ಌ': 'ḻ'
+    'ೡ': 'ḹ'
+    'ಎ': 'e'
+    'ಏ': 'ē'
+    'ಐ': 'ai'
+
+    'ಒ': 'o'
+    'ಓ': 'ō'
+    'ಔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ಕ': 'ka'
+    'ಖ': 'kha'
+    'ಗ': 'ga'
+    'ಘ': 'gha'
+    'ಙ': 'ṅa'
+
+    # Palatals
+    'ಚ': 'ca'
+    'ಛ': 'cha'
+    'ಜ': 'ja'
+    'ಝ': 'jha'
+    'ಞ': 'ña'
+
+    # Cerebrals
+    'ಟ': 'ṭa'
+    'ಠ': 'ṭha'
+    'ಡ': 'ḍa'
+    'ಢ': 'ḍha'
+    'ಣ': 'ṇa'
+
+    # Dentals
+    'ತ': 'ta'
+    'ಥ': 'tha'
+    'ದ': 'da'
+    'ಧ': 'dha'
+    'ನ': 'na'
+
+    # Labials
+    'ಪ': 'pa'
+    'ಫ': 'pha'
+    'ಬ': 'ba'
+    'ಭ': 'bha'
+    'ಮ': 'ma'
+
+    # Semivowels
+    'ಯ': 'ya'
+    'ರ': 'ra'
+    'ಱ': 'ṟa'
+    'ಲ': 'la'
+    'ಳ': 'ḷa'
+    'ವ': 'va'
+
+    # Sibilants
+    'ಶ': 'śa'
+    'ಷ': 'ṣa'
+    'ಸ': 'sa'
+
+
+    # Aspirate
+    'ಹ': 'ha'
+
+    'ಜ಼': 'za'
+    'ಫ಼': 'fa'
+
+    # Bisarga
+    'ಃ': 'ḥ'
+
+    'ೱ': 'ẖ'
+    'ೲ': 'ḫ'
+
+
+    # candrabindu
+    '\u0C80': 'm̐'
+    '\u0C81': 'm̐'
+
+    # Abagraha
+    'ಽ': ':’' # (apostrophe)
+
+    # Anusvāra
+    'ಂ': 'ṁ'
+
+    '಼': '' #nukta
+
+    # Medials # Needed for connecting constants
+    'ಾ': "ā"
+    'ಿ': "i"
+    'ೀ': "ī"
+    'ು': "u"
+    'ೂ': "ū"
+
+    'ೃ': "ṛ"
+    'ೄ': "ṝ"
+    ' ೢ': 'ḷ'
+    ' ೣ': 'ḹ'
+
+    'ೆ': "e"
+    'ೇ': "ē"
+    'ೈ': "ai"
+
+
+    'ೊ': 'o'
+    'ೋ': 'ō'
+    'ೌ': 'au'
+
+    '्': ''
+    '़': ''
+    '್': ''
+    "‍": '' # no need for zero with joiner
+    "‌": '' # no need for zero with non joiner ': 'ya'
+
+
+    # for semivowel rule no. 5
+    'ಯಀ': 'm̐ya'
+    'ರಀ': 'm̐ra'
+    'ಱಀ': 'm̐ṟa'
+    'ಲಀ': 'm̐la'
+    'ಳಀ': 'm̐ḷa'
+    'ವಀ': 'm̐va'
+
+    # numbers
+
+    '೧': '1'
+    '೨': '2'
+    '೩': '3'
+    '೪': '4'
+    '೫': '5'
+    '೬': '6'
+    '೭': '7'
+    '೮': '8'
+    '೯': '9'
+    '೦': '0'

data/maps/iso-kat-Geor-Latn-9984-1996.yaml

@@ -0,0 +1,145 @@
+---
+authority_id: iso
+id: 9984-1996
+language: iso-639-2:kat
+source_script: Geor
+destination_script: Latn
+name: "ISO 9984:1996 Information and documentation — Transliteration of Georgian characters into Latin characters"
+url: https://www.iso.org/standard/17892.html
+creation_date: 1996
+confirmation_date: 1996
+description: |
+  Establishes a system for the transliteration of Georgian characters
+  into Latin characters to permit international information exchange,
+  particularly by electronic means.
+
+notes:
+
+tests:
+
+  - source: ხაოფსე
+    expected: xaop̕se
+
+  - source: ჭლოუ
+    expected: člou
+
+  - source: ჩოხულდი
+    expected: č̕oxuldi
+
+  - source: ქვემო ლინდა
+    expected: k̕vemo linda
+
+  - source: ტამკვაჩ იგვავერა
+    expected: tamkvač̕ igvavera
+
+  - source: სვანეთი
+    expected: svanet̕i
+
+  - source: საცხვარისი
+    expected: sac̕xvarisi
+
+  - source: მუხრან-თელეთი
+    expected: muxran-t̕elet̕i
+
+  - source: მუცდი
+    expected: muc̕di
+
+  - source: ლეჩხუმი
+    expected: leč̕xumi
+
+  - source: ვერხნაია მწარა
+    expected: verxnaia mcara
+
+  - source: ეგრისის ქედი
+    expected: egrisis k̕edi
+
+  - source: დოჩარიფშა
+    expected: doč̕arip̕ša
+
+  - source: ბოლოკო
+    expected: boloko
+
+  - source: აჭანდარა
+    expected: ačandara
+
+  - source: აუალიცა
+    expected: aualic̕a
+
+  - source: აკალამრა
+    expected: akalamra
+
+  - source: ლასილი
+    expected: lasili
+
+  - source: გუბაზეული
+    expected: gubazeuli
+
+  - source: ბაყაყი
+    expected: baqaqi
+
+  - source: ძროხა
+    expected: jroxa
+
+  - source: ჰაერი
+    expected: haeri
+
+  - source: ჟოლო
+    expected: žolo
+
+  - source: ჯართი
+    expected: ǰart̕i
+
+  - source: ღრმაღელე
+    expected: ḡrmaḡele
+
+map:
+  characters:
+    '\u10d0' : 'a' # ა
+    '\u10d1' : 'b' # ბ
+    '\u10d2' : 'g' # გ
+    '\u10d3' : 'd' # დ
+    '\u10d4' : 'e' # ე
+    '\u10d5' : 'v' # ვ
+    '\u10d6' : 'z' # ზ
+
+    '\u10f1' : 'ē' # ჱ
+
+    '\u10d7' : 't̕' # თ
+    '\u10d8' : 'i' # ი
+    '\u10d9' : 'k' # კ
+    '\u10da' : 'l' # ლ
+    '\u10db' : 'm' # მ
+    '\u10dc' : 'n' # ნ
+
+    '\u10f2' : 'y' # ჲ
+
+    '\u10dd' : 'o' # ო
+    '\u10de' : 'p' # პ
+    '\u10df' : 'ž' # ჟ
+    '\u10e0' : 'r' # რ
+    '\u10e1' : 's' # ს
+    '\u10e2' : 't' # ტ
+
+    '\u10f3' : 'w' # ჳ
+
+    '\u10e3' : 'u' # უ
+    '\u10e4' : 'p̕' # ფ
+    '\u10e5' : 'k̕' # ქ
+    '\u10e6' : 'ḡ' # ღ
+    '\u10e7' : 'q' # ყ
+    '\u10e8' : 'š' # შ
+    '\u10e9' : 'č̕' # ჩ
+    '\u10ea' : 'c̕' # ც
+    '\u10eb' : 'j' # ძ
+    '\u10ec' : 'c' # წ
+    '\u10ed' : 'č' # ჭ
+    '\u10ee' : 'x' # ხ
+
+    '\u10f4' : 'ẖ' # ჴ
+
+    '\u10ef' : 'ǰ' # ჯ
+    '\u10f0' : 'h' # ჰ
+
+    '\u10f5' : 'ō' # ჵ
+
+    '\u10f6' : 'f' # ჶ

data/maps/iso-kor-Hang-Latn-1996-method1.yaml

@@ -0,0 +1,240 @@
+---
+authority_id: iso
+id: 1996-method1
+language: iso-639-2:kor
+source_script: Hang
+destination_script: Latn
+name: "ISO/TR 11941:1996 Information and documentation — Transliteration of Korean script into Latin characters"
+url: https://www.iso.org/standard/20564.html
+creation_date: 1996
+adoption_date:
+description: Establishes a system for the transliteration of the characters of Korean script into Latin characters. Intended to provide a means for international communication of written documents.
+
+notes: ""
+
+tests:
+  # Tests from https://www.eki.ee/wgrs/rom2_ko.pdf
+  - source: "꽃이"
+    expected: "kkoch'i" # Bad OCR
+  - source: "강에"
+    expected: "kang'e"
+  - source: "앉아라"
+    expected: "anc'ara"
+  - source: "아까"
+    expected: "a'kka"
+  - source: "흰떡"
+    expected: "hyin'tteok"
+  - source: "유쾌하다"
+    expected: "yu'khwaehata"
+
+  # Tests from https://github.com/interscript/interscript/files/5249245/ISO-TR-11941-1996.pdf
+  - source: "애기"
+    expected: "aeki"
+  - source: "방"
+    expected: "pang"
+  - source: "아이"
+    expected: "a'i"
+  - source: "고양이"
+    expected: "ko'yang'i"
+  - source: "굽이"
+    expected: "kup'i"
+  - source: "밖에"
+    expected: "pakk'e"
+  - source: "박게"
+    expected: "pakke"
+  - source: "바께"
+    expected: "pa'kke"
+  - source: "간게"
+    expected: "kanke"
+  - source: "안자라"
+    expected: "ancara"
+  - source: "오빠"
+    expected: "o'ppa"
+  - source: "어찌"
+    expected: "eo'cci"
+  - source: "아씨"
+    expected: "a'ssi"
+  - source: "애타다"
+    expected: "ae'thata"
+  - source: "아프다"
+    expected: "a'pheuta"
+  - source: "기차다"
+    expected: "ki'chata"
+  - source: "동녘에"
+    expected: "tongnyeokh'e"
+  - source: "같이"
+    expected: "kath'i"
+  - source: "앞에"
+    expected: "aph'e"
+  - source: "꽃에"
+    expected: "kkoch'e"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: False
+  inherit: var-kor-Hang-Hang-jamo
+
+  rules:
+
+  postrules:
+    # Add space to the two ends of the string for easier word boundary handling
+    - pattern: "^"
+      result: " "
+    - pattern: "$"
+      result: " "
+
+    # Marks A, B, C
+    - pattern: "(?<!\\p{Hangul})ᄋ" # Word initially
+      result: ""
+    - pattern: "ᄋ" # See notes 2, 3 and 4.
+      result: "'"
+    - pattern: "ᆼ" # At the end of a syllable.
+      result: "ng"
+
+    # Note 4: add apostrophe before 5 double consonants at initial position
+    #         unless start of the word
+    - pattern: "(?<=\\p{Hangul})([ᄁᄄᄈᄍᄊ])"
+      result: "'\\1"
+    # Note 4: (only method 1) same but with 4 aspirated
+    - pattern: "(?<=\\p{Hangul})([ᄏᄐᄑᄎ])"
+      result: "'\\1"
+
+    # Consonants differing between method1 and method2
+    - pattern: "[ᄀᆨ]"
+      result: "k"
+    - pattern: "[ᄏᆿ]"
+      result: "kh"
+    - pattern: "[ᄁᆩ]"
+      result: "kk"
+    - pattern: "[ᄃᆮ]"
+      result: "t"
+    - pattern: "[ᄐᇀ]"
+      result: "th"
+    - pattern: "[ᄄퟍ]"
+      result: "tt"
+    - pattern: "[ᄇᆸ]"
+      result: "p"
+    - pattern: "[ᄑᇁ]"
+      result: "ph"
+    - pattern: "[ᄈퟦ]"
+      result: "pp"
+    - pattern: "[ᄌᆽ]"
+      result: "c"
+    - pattern: "[ᄎᆾ]"
+      result: "ch"
+    - pattern: "[ᄍퟹ]"
+      result: "cc"
+    # End
+
+    # Composite differing consonants (cons. https://en.wikipedia.org/wiki/ISO/TR_11941 )
+    - pattern: "[ᆪ]"
+      result: "ks"
+    - pattern: "[ꥤ]" # D. R at the beginning of a syllable
+      result: "rk"
+    - pattern: "[ᆰ]"
+      result: "lk"
+    - pattern: "[ᆴ]"
+      result: "lth"
+    - pattern: "[ꥩ]" # D. R at the beginning of a syllable
+      result: "rp"
+    - pattern: "[ᆲ]"
+      result: "lp"
+    - pattern: "[ᆵ]"
+      result: "lph"
+    - pattern: "[ᅜᆬ]"
+      result: "nc"
+    - pattern: "[ᄡᆹ]"
+      result: "ps"
+    # End
+
+    # Other consonants
+    - pattern: "[ᄉᆺ]"
+      result: "s"
+    - pattern: "[ᄊᆻ]"
+      result: "ss"
+    - pattern: "[ᄒᇂ]"
+      result: "h"
+    - pattern: "[ᄂᆫ]"
+      result: "n"
+    - pattern: "[ᄅ]" # D. R at the beginning of a syllable.
+      result: "r"
+    - pattern: "[ᆯ]"
+      result: "l"
+    - pattern: "[ᄆᆷ]"
+      result: "m"
+    # End
+
+    # Other composite consonants (cons. https://en.wikipedia.org/wiki/ISO/TR_11941 )
+    - pattern: "[ꥬ]" # D. R at the beginning of a syllable
+      result: "rs"
+    - pattern: "[ᆳ]"
+      result: "ls"
+    - pattern: "[ꥨ]" # D. R at the beginning of a syllable
+      result: "rm"
+    - pattern: "[ᆱ]"
+      result: "lm"
+    - pattern: "[ᄚ]" # D. R at the beginning of a syllable
+      result: "rh"
+    - pattern: "[ᆶ]"
+      result: "lh"
+    - pattern: "[ᅝᆭ]"
+      result: "nh"
+    # End
+
+    # Vowels
+    - pattern: "ᅡ"
+      result: "a"
+    - pattern: "ᅥ"
+      result: "eo"
+    - pattern: "ᅩ"
+      result: "o"
+    - pattern: "ᅮ"
+      result: "u"
+    - pattern: "ᅳ"
+      result: "eu"
+    - pattern: "ᅵ"
+      result: "i"
+    - pattern: "ᅢ"
+      result: "ae"
+    - pattern: "ᅦ"
+      result: "e"
+    - pattern: "ᅬ"
+      result: "oe"
+    - pattern: "ᅣ"
+      result: "ya"
+    - pattern: "ᅧ"
+      result: "yeo"
+    - pattern: "ᅭ"
+      result: "yo"
+    - pattern: "ᅲ"
+      result: "yu"
+    - pattern: "ᅤ"
+      result: "yae"
+    - pattern: "ᅨ"
+      result: "ye"
+    - pattern: "ᅪ"
+      result: "wa"
+    - pattern: "ᅯ"
+      result: "weo"
+    - pattern: "ᅱ"
+      result: "wi"
+    - pattern: "ᅫ"
+      result: "wae"
+    - pattern: "ᅰ"
+      result: "we"
+    - pattern: "ᅴ"
+      result: "yi"
+    # End
+
+    # Remove space added
+    - pattern: "^ "
+      result: ""
+    - pattern: " $"
+      result: ""
+
+  characters:
+  # This is based on Jamo
+
+  dictionary:
+  #