interscript 0.1.9 → 2.0.5

data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml

@@ -1,253 +0,0 @@
----
-authority_id: bgnpcgn
-id: kn-1945
-language: iso-639-2:kor
-source_script: Hang
-destination_script: Latn
-name: BGN/PCGN 1945 Agreement
-url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693725/ROMANIZATION_OF_KOREAN-_MR_for_DPRK.pdf
-creation_date: 1945
-adoption_date:
-description:
-
-notes: "
-
-  1. At the end of a syllable, the character ᄋ should be romanized ng,
-     as in the following example:
-
-     평양 → P’yŏngyang
-
-     At the beginning of a syllable, the character ᄋ is silent and
-     should not be romanized. An example follows:
-
-     용화 → Yonghwa
-
-  2. Syllable boundaries within words are not reflected in romanization.
-     In the different types of syllables shown in the table below, C
-     represents any consonant character, V represents any vowel character
-     and / represents a syllable boundary.
-
-       Han’gŭl              개성      남포      안양
-       Syllable boundaries  CV/CVC   CVC/CV   VC/VC
-       Romanization         Kaesŏng  Namp’o   Anyang
-
-  3. Euphonic changes occurring within a word, including between the
-     specific and generic of a geographical name, should be reflected in
-     romanization. Generic terms are usually seen separated from the name
-     by a hyphen and with a lower case initial letter rather than as a
-     separate word:
-
-       영진리 → Yŏngjil-li
-       덕흥리 → Tŏkhŭng-ni
-       압록강 → Amnok-kang
-       대동강 → Taedong-gang
-
-  4. As a result of 조선말규범집 (‘Standard Korean Language’ guidelines
-     published in North Korea in 1966), unlike the Korean spoken in the
-     Republic of Korea, the language spoken in the Democratic People’s
-     Republic of Korea maintains and pronounces the word-initial ᆯ (‘r’).
-     The use of the word-initial ᄅ ('r') can be seen in official news
-     reports as well as native mapping. Since such examples exist, the
-     word initial ᄅ ('r') is reflected as an option in the tables given above.
-
-  5. The Romanization column shows only lowercase forms but, when romanizing,
-     uppercase and lowercase Roman letters as appropriate should be used.
-  "
-
-tests:
-  - source: "평양"
-    expected: "P’yŏngyang"
-  - source: "용화"
-    expected: "Yonghwa"
-  - source: "개성"
-    expected: "Kaesŏng"
-  - source: "남포"
-    expected: "Namp’o"
-  - source: "안양"
-    expected: "Anyang"
-  - source: "영진-리"
-    expected: "Yŏngjil-li"
-  - source: "덕흥-리"
-    expected: "Tŏkhŭng-ni"
-  - source: "압록-강"
-    expected: "Amnok-kang"
-  - source: "대동-강"
-    expected: "Taedong-gang"
-  - source: "라선특별시"
-    expected: "Rasŏnt’ŭkpyŏlsi"
-  - source: 은하-리
-    expected: "Ŭnha-ri"
-  - source: 은중-리
-    expected: "Ŭnjung-ni"
-  - source: 은장-령
-    expected: "Ŭnjang-nyŏng"
-  - source: 은혜-동
-    expected: "Ŭnhye-dong"
-  - source: 은호-리
-    expected: "Ŭnho-ri"
-  - source: 은행정
-    expected: "Ŭnhaengjŏng"
-  - source: 은행-동
-    expected: "Ŭnhaeng-dong"
-  - source: 은행-촌
-    expected: "Ŭnhaeng-ch’on"
-  - source: 원수
-    expected: "Wŏnsu"
-  - source: 원소리-고개
-    expected: "Wŏnsori-gogae"
-  - source: 원소참
-    expected: "Wŏnsoch’am"
-  - source: 원소-리
-    expected: "Wŏnso-ri"
-  - source: 원신-리
-    expected: "Wŏnsil-li"
-  - source: 난곡
-    expected: "Nan’gok"
-  - source: 난산-리
-    expected: "Nansal-li"
-  - source: 난직
-    expected: "Nanjik"
-  - source: 영곡
-    expected: "Yŏnggok"
-  - source: 윗두밀
-    expected: "Wittumil"
-  - source: 윗도심이
-    expected: "Wittosimi"
-  - source: 둔지
-    expected: "Tunji"
-  - source: 서승
-    expected: "Sŏsŭng"
-  - source: 신촌
-    expected: "Sinch’on"
-  - source: 비암덕
-    expected: "Piamdŏk"
-  - source: 바위안
-    expected: "Pawian"
-  - source: 오송평
-    expected: "Osongp’yŏng"
-  - source: 그물목
-    expected: "Kŭmulmok"
-  - source: 구원정
-    expected: "Kuwŏnjŏng"
-  - source: 일하
-    expected: "Irha"
-  - source: 황우
-    expected: "Hwangu"
-  - source: 자작보
-    expected: "Chajakpo"
-  - source: 비파1-동
-    expected: "Pip’a Il-tong"
-  - source: 문암 오-동
-    expected: "Munam O-dong"
-
-map:
-  character_separator: ""
-  word_separator: " "
-  title_case: True
-  inherit: [var-kor-Hang-Latn-mr-1939]
-
-  rules:
-    # Add Zero-width White-space U+200B after spaces (i.e. before word boundaries)
-    # So that the word-initial conversion rules will be blocked.
-    - pattern: "^"
-      result: "\u200B"
-    - pattern: "(?<= )"
-      result: "\u200B"
-
-    # convert numbers to space + Hangul
-    - pattern: "([^0-9 ])(?=[0-9])"
-      result: "\\1 "
-    - pattern: "1"
-      result: "일"
-    - pattern: "2"
-      result: "이"
-    - pattern: "3"
-      result: "삼"
-    - pattern: "4"
-      result: "사"
-    - pattern: "5"
-      result: "오"
-    - pattern: "6"
-      result: "육"
-    - pattern: "7"
-      result: "칠"
-    - pattern: "8"
-      result: "팔"
-    - pattern: "9"
-      result: "구"
-
-    # This is a logic to add hyphen in front of generics
-    # - pattern: "(?<=.)(구역|동|리|도|고개|골|로동자구|사무소|초등학교|중학교|고등학교|강|포|령|역|봉|사|천|교|제|저수지|소류지|재|못|말|면|암|교회|촌|병원|바위|공원|섬|우체국|대학교|보건소|굴|치|대교|지구|폭포|해수욕장|휴게소|중고교|읍|보건진료소|마을|톨게이트|대학|시장|경찰서|학교)$" #to be expanded
-    #   result: "-\\1"
-
-  postrules:
-
-    # Add space to the two ends of the string for easier word boundary handling
-    - pattern: "^"
-      result: " "
-    - pattern: "$"
-      result: " "
-
-    # Initial rules in the inherited map were blocked, so that
-    # this set of updated rules (with the onset rules removed) will be used instead.
-    - pattern: "\u200B"
-      result: ""
-
-    - pattern: "(?<= )ᄀ"
-      result: "k" # HANGUL CHOSEONG KIYEOK
-    - pattern: "(?<= )ᄂ"
-      result: "n" # HANGUL CHOSEONG NIEUN
-    - pattern: "(?<= )ᄃ(?=[ᅵᅣᅤᅧᅨᅭᅲ])"
-      result: "ch" # HANGUL CHOSEONG TIEUT # T -> Ch before yotized vowels
-    - pattern: "(?<= )ᄃ"
-      result: "t" # HANGUL CHOSEONG TIEUT
-    - pattern: "(?<= )ᄅ"
-      result: "r" # HANGUL CHOSEONG RIEUL
-    - pattern: "(?<= )ᄆ"
-      result: "m" # HANGUL CHOSEONG MIEUM
-    - pattern: "(?<= )ᄇ"
-      result: "p" # HANGUL CHOSEONG PIEUP
-    - pattern: "(?<= )ᄉ(?=ᅱ)"
-      result: "sh" # HANGUL CHOSEONG SIOS
-    - pattern: "(?<= )ᄉ"
-      result: "s" # HANGUL CHOSEONG SIOS
-    - pattern: "(?<= )ᄋ"
-      result: "" # HANGUL CHOSEONG IEUNG
-    - pattern: "(?<= )ᄌ"
-      result: "ch" # HANGUL CHOSEONG CIEUC
-    - pattern: "(?<= )ᄎ"
-      result: "ch’" # HANGUL CHOSEONG CHIEUCH
-    - pattern: "(?<= )ᄏ"
-      result: "k’" # HANGUL CHOSEONG KHIEUKH
-    - pattern: "(?<= )ᄐ(?=[ᅵᅣᅤᅧᅨᅭᅲ])"
-      result: "ch’" # HANGUL CHOSEONG THIEUTH + YOTIZED VOWELS
-    - pattern: "(?<= )ᄐ"
-      result: "t’" # HANGUL CHOSEONG THIEUTH
-    - pattern: "(?<= )ᄑ"
-      result: "p’" # HANGUL CHOSEONG PHIEUPH
-    - pattern: "(?<= )ᄒ"
-      result: "h" # HANGUL CHOSEONG HIEUH
-    - pattern: "(?<= )ᄁ"
-      result: "kk" # HANGUL CHOSEONG SSANGKIYEOK
-    - pattern: "(?<= )ᄭ"
-      result: "kk" # HANGUL CHOSEONG SIOS-KIYEOK
-    - pattern: "(?<= )ᄄ"
-      result: "tt" # HANGUL CHOSEONG SSANGTIEUT
-    - pattern: "(?<= )ᄯ"
-      result: "tt" # HANGUL CHOSEONG SIOS-TIEUT
-    - pattern: "(?<= )ᄈ"
-      result: "pp" # HANGUL CHOSEONG SSANGPIEUP
-    - pattern: "(?<= )ᄲ"
-      result: "pp" # HANGUL CHOSEONG SIOS-PIEUP
-    - pattern: "(?<= )ᄊ"
-      result: "ss" # HANGUL CHOSEONG SSANGSIOS
-    - pattern: "(?<= )ᄍ"
-      result: "tch" # HANGUL CHOSEONG SSANGCIEUC
-    - pattern: "(?<= )ᄶ"
-      result: "tch" # HANGUL CHOSEONG SIOS-CIEUC
-
-    # Remove space added
-    - pattern: "^ "
-      result: ""
-    - pattern: " $"
-      result: ""

data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml

@@ -1,48 +0,0 @@
----
-authority_id: bgnpcgn
-id: 2011
-language: iso-639-2:kor
-source_script: Hang
-destination_script: Latn
-name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
-url:
-creation_date:
-adoption_date:
-description:
-
-notes:
-  BGN/PCGN 2011 Agreement
-
-tests:
-  - source: 불국사
-    expected: "Bulguksa"
-  - source: 묵호
-    expected: "Mukho"
-  - source: 울산
-    expected: "Ulsan"
-  - source: 독립문
-    expected: "Dongnimmun"
-  - source: 강남역
-    expected: "Gangnamyeok"
-  - source: 남산리
-    expected: "Namsan-ri" #Note: no assimilation for -ri even after nasals
-  - source: 내월리
-    expected: "Naewol-ri"
-  - source: 울릉군
-    expected: "Ulleung-gun"
-  - source: 설악산
-    expected: "Seoraksan"
-  - source: 삼죽면
-    expected: "Samjuk-myeon"
-  - source: 평리1동
-    expected: "Pyeongni Il-dong"
-  - source: 평리2동
-    expected: "Pyeongni I-dong"
-  - source: 탑안이
-    expected: "Tabani"
-
-map:
-  character_separator: ""
-  word_separator: " "
-  title_case: True
-  inherit: moct-kor-Hang-Latn-2000

data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml

@@ -1,48 +0,0 @@
----
-authority_id: bgnpcgn
-id: 2011
-language: iso-639-2:kor
-source_script: Kore
-destination_script: Latn
-name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
-url:
-creation_date:
-adoption_date:
-description:
-
-notes:
-  BGN/PCGN 2011 Agreement
-
-tests:
-  - source: 佛國寺
-    expected: "Bulguksa"
-  - source: 묵호
-    expected: "Mukho"
-  - source: 蔚山
-    expected: "Ulsan"
-  - source: 獨立門
-    expected: "Dongnimmun"
-  - source: 江南驛
-    expected: "Gangnamyeok"
-  - source: 南山里
-    expected: "Namsan-ri" #Note: no assimilation for -ri even after nasals
-  - source: 내월里
-    expected: "Naewol-ri"
-  - source: 鬱陵郡
-    expected: "Ulleung-gun"
-  - source: 雪嶽山
-    expected: "Seoraksan"
-  - source: 三竹面
-    expected: "Samjuk-myeon"
-  - source: 坪里1洞
-    expected: "Pyeongni Il-dong"
-  - source: 坪里2洞
-    expected: "Pyeongni I-dong"
-  - source: 탑안이
-    expected: "Tabani"
-
-map:
-  character_separator: ""
-  word_separator: " "
-  title_case: True
-  inherit: [var-kor-Kore-Hang-2013, moct-kor-Hang-Latn-2000]

data/maps/bgnpcgn-kur-Arab-Latn-2007.yaml

@@ -1,249 +0,0 @@
----
-authority_id: bgnpcgn
-id: 2007
-language: kur
-source_script: Arab
-destination_script: Latn
-name: ROMANIZATION OF KURDISH -- BGN/PCGN 2007
-url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693727/ROMANIZATION_OF_KURDISH.pdf
-creation_date: 2007
-confirmation date: 2017-12
-description: |
-  The tabulation below is applicable to the Kurdish language as a
-  whole. It is based for the most part on the Hawar Roman alphabet used
-  in the Library of Congress Standard Kurdish Orthography Table, but it
-  also incorporates certain non-Hawar elements found in A Kurdish-English
-  Dictionary (Taufiq Wahby & C J Edmonds, OUP, 1966). The tabulation
-  covers both major varieties of the Kurdish language: Kurmanji and
-  Sorani. Kurmanji is spoken principally in Turkey and in Iraq north of
-  the Great Zab River (Dahūk/Dihok Governorate). It is generally written
-  in Roman script, and usually employs the Roman orthography. Sorani is
-  spoken principally in Iraq south of the Great Zab river (Arbīl/Hewlêr
-  and As Sulaymānīyah/Slêmanî governorates). It is generally written in
-  Perso-Arabic script, and usually employs the Perso-Arabic script
-  orthography.
-
-  Kurdish forms of geographical names in Turkey will usually be found
-  in Roman script, and so no romanization process will be required. The
-  digraph options for consonant letters '\u0686', '\u0634', and '\u063A'
-  will not be encountered for such names. In Iraq, Syria, and Iran,
-  Kurdish will usually be encountered in Perso-Arabic script, in which
-  case it should be romanized into the corresponding Roman script form.
-  Kurdish geographical names for places and features outside Turkey,
-  found in Roman script form, should, where necessary and if possible, be
-  tailored to fit the orthography of the Romanization shown below and
-  should employ the digraph options for consonant letters '\u0686',
-  '\u0634', and '\u063A'.
-
-notes:
-
-  - In pure Kurdish words hamza is borne by yā’ ( ئ ) and occurs only
-    before initial vowels; it is not romanized. Medial and final hamza in
-    Arabic borrowings are romanized by ’ (apostrophe – Unicode encoding
-    2019).
-
-  - The letters ث ذ ص ض ط ظ do not occur in pure Kurdish words. In Arabic
-    borrowings some writers retain these letters, others substitute س ز س ز
-    ت ز respectively. Only the letters ط ض and ص are catered for in the
-    Library of Congress tabulation, as reflected in lines 16-18 of the
-    above Consonant table. Words of obvious Arabic origin occurring in a
-    Kurdish toponymic environment will be treated as Kurdish rather than
-    Arabic, as will words of other non-Kurdish origins.
-
-  - The digraph options appearing in rows 6, 15 and 20 of the consonants
-    table should be used for Kurdish geographical names in Iraq, Iran, and
-    Syria. The single character options should be used for Kurdish
-    geographical names in Turkey.
-
-  - ڨ is used to represent v in foreign words. Some southern Kurdish
-    writers use it to represent the v in borrowings from northern Kurdish
-    dialects. و is pronounced as a v in the north and as a w elsewhere.
-
-  - Hā’ can be used as a vowel or a consonant. The initial (ه) and medial
-    (forms are used for the consonant h, Consonant table, row 31, while the
-    final (ه) and independent (forms are used to represent the vowel e,
-    Vowel table, row 1. Therefore, when used as a consonant, the final and
-    independent forms of hā’ will be seen as ‘ه’ instead of ‘and ‘ه’,
-    respectively. For example, مهه meh, (“month”). When used as ‘e’, the
-    hā’ behaves like the letters alif (ا) , wāw, dāl (د) , and rā (ر) , in
-    that it never joins to the following letter (i.e., it has no medial
-    form). Consequently, the following letter will display the initial
-    form, e.g. هەولێر Hewlêr (unless there is only one following letter, in
-    which case it will be written in the independent form, e.g. ماوەت
-    Mawet). As with other vowels (see special rules 2 and 3), initial e is
-    preceded by the kursî hamza, yielding initial ئه , e.g. ئهني enî
-    “forehead”.
-
-  - In pure Kurdish words, the vowel ى is always long î, e.g. كانى ماسێ
-    Kanî Masê. When it represents îzafe, it is also romanized î and joined
-    by means of a hyphen to its preceding word e.g. پارێزگاى دهۆك Parêzga-î
-    Dihok.
-
-  - |
-    An inventory of letter-diacritic combinations, used in addition to
-    the unmodified letters of the basic Roman script in the Romanization of
-    Kurdish, with their Unicode encoding, is:
-
-      '‘': '\u2018' , '’': '2019'
-      'Ç': '00C7' , 'ç': '00E7'
-      'Ḍ': '1E0C' , 'ḍ': '1E0D'
-      'Ê': '00CA' , 'ê': '00EA'
-
-      # There is no single Unicode encoding for these letter-diacritic combinations.
-      'Ḧ': '0048+0308' , 'ḧ': '0068+0308'
-      'Î': '00CE' , 'î': '00EE'
-      'Ł': '0141' , 'ł': '0142'
-      'Ö': '00D6' , 'ö': '00F6'
-      'Ṟ': '1E5E' , 'ṟ': '1E5F'
-      'Ş': '015E' , 'ş': '015F'
-      'Ṣ': '1E62' , 'ṣ': '1E63'
-      'Ṭ': '1E6C' , 'ṭ': '1E6D'
-      'Û': '00DB' , 'û': '00FB'
-      'Ü': '00DC' , 'ü': '00FC'
-      'Ẍ': '1E8C' , 'ẍ': '1E8D'
-
-  - The Romanization column shows only lowercase forms but, when
-    romanizing, uppercase and lowercase Roman letters as appropriate should
-    be used.
-
-  # Special Rules
-  - The conjunction و (and) should be rendered u if the
-    preceding word ends in a consonant, and w if the preceding
-    word ends in a vowel. It should be separated by spaces from
-    the preceding and following words.
-
-  - In the Perso-Arabic orthography for Kurdish, all vowels are
-    written, with the exception of the short i, which is
-    expressed with a kasrah under the preceding consonant (ِ).
-    In Perso-Arabic script, the kasrah will rarely be written (
-    e.g., كرن kirin “to do”). Like all Kurdish vowels, the
-    short i will be preceded by a kursî hamza )ئ )if it appears
-    at the beginning of a word (see 3 below; see row 4 of vowel
-    table).
-
-  - In the Perso-Arabic orthography for Kurdish, when a vowel
-    comes at the beginning of a word, or when a vowel directly
-    follows another vowel, a kursî hamza )ئ )precedes it (e.g.,
-    ئاگر agir “fire”).
-
-  - A Kurdish word will never start with alif )ا .)A Kurdish
-    word may begin with a yā’ (ي) or wāw )و ,)but only when
-    they are used as a consonant, when they will be romanized
-    as y and w, respectively.
-
-  - When preceded by a consonant, yā’ (ي )and wāw )و )should be
-    romanized î and u, respectively. When preceded by a vowel (
-    including short i, which is not written), yā’ (ي )and wāw (
-    و )should be romanized y and w, respectively.
-
-  - The Arabic sign shaddah ( ّ ) denoting a doubled consonant
-    is not used in Kurdish; doubled consonants, which are rare,
-    are written twice e.g. موحەممەد Muḧemmed; ننا موسه Musanna.
-    Shaddah might be used in Arabic borrowings but, as in
-    unpointed Arabic, would generally be omitted.
-
-  - Particles such as له le (= at, in, on) and به be (= to,
-    for, by, with) should be written separately from their
-    following word, e.g. كوردستانێ له Le Kurdistanê “in
-    Kurdistan”
-
-  - Occasionally the character sequences چه ,سه and گه occur.
-    They may be romanized c·h, s·h, and g·h in order to
-    differentiate those romanizations from the digraphs ch, sh,
-    and gh.
-
-tests:
-  - source: كاني ماسێ
-    expected: Kanî Masê
-
-  - source: كِرِن
-    expected: Kirin
-
-  - source: ئاگِر
-    expected: Agir
-
-  - source: موحەممەد
-    expected: Muḧemmed
-
-  # - source: موسەننا # issue 604
-  #   expected: Musanna
-
-  - source: لەكوردِستانێ
-    expected: Le Kurdistanê
-
-map:
-  postrules:
-    - pattern: (?<=\b)(?<!\b[‘|’|'])[\u0061-\uFFFF]
-      result: "upcase"
-
-  characters:
-
-    '\u0650' : 'i' # ِ kasra special rule 2
-    '\u0644\u06d5' : 'le ' # special rule 7
-    '\u0628\u06d5' : 'be ' # special rule 7
-    # Note 1
-    '\u0621' : '’' # ء
-    '\u0624' : '’' # ؤ
-    '\u0626' : '’' # ئ
-
-    "(?<=[\u0621|\u0628|\u067E|\u062A|\u062C|\u0686|\u062D|\u062E|\u062F|\u0631|\u0695|\u0632|\u0698|\u0633|\u0634|\u0635|\u0636|\u0637|\u0639|\u063A|\u0341|\u06A8|\u0642|\u06A9|\u0643|\u06AF|\u0644|\u06B5|\u0645|\u0646|\u0648|\u0647|\u064A])\u0648" : 'u' # special note 4/5
-    "(?<=[\u0621|\u0628|\u067E|\u062A|\u062C|\u0686|\u062D|\u062E|\u062F|\u0631|\u0695|\u0632|\u0698|\u0633|\u0634|\u0635|\u0636|\u0637|\u0639|\u063A|\u0341|\u06A8|\u0642|\u06A9|\u0643|\u06AF|\u0644|\u06B5|\u0645|\u0646|\u0648|\u0647|\u064A])\u064A" : 'î' # special note 4/5
-    '\u0621': '’' # ء (see note 1 and 7)
-    '\u0628': 'b'  # ب
-    '\u067E': 'p'  # پ
-    '\u062A': 't'  # ت (see note 2)
-    '\u062C': 'c'  # ج
-    '\u0686': # چ (see notes 3 and 7)
-      - 'ch'
-      - 'ç'
-    '\u062D': 'ḧ'  # ح
-    '\u062E': 'x'  # خ
-    '\u062F': 'd'  # د
-    '\u0631': 'r'  # ر
-    '\u0695': 'ṟ'  # ڕ (Formerly written ڒ ڔ or رر according to typeface available; may vary on older sources. See note 7.)
-    '\u0632': 'z'  # ز (see note 2)
-    '\u0698': 'j'  # ژ
-    '\u0633': 's'  # س (see note 2)
-    '\u0634': # ش (see notes 3 and 7)
-      - 'sh'
-      - 'ş'
-    '\u0635': 'ṣ'  # ص (see notes 2 and 7)
-    '\u0636': 'ḍ'  # ض (see notes 2 and 7)
-    '\u0637': 'ṭ'  # ط  (see notes 2 and 7)
-    '\u0639': '‘'  # ع  (see note 7)
-    '\u063A': # غ (see notes 3 and 7)
-      - 'gh'
-      - 'ẍ'
-    '\u0341': 'f'  # ف
-    '\u06A8': 'v'  # ڨ  (see note 4)
-    '\u0642': 'q'  # ق
-    '\u06A9': 'k'  # ك
-    '\u0643': 'k'  # ك
-    '\u06AF': 'g'  # گ
-    '\u0644': 'l'  # ل
-    '\u06B5': 'ł'  # ڵ  (Formerly written ڶ according to type available; may vary on older sources. See note 7)
-    '\u0645': 'm'  # م
-    '\u0646': 'n'  # ن
-    '\u0648': 'w'  # و  (see note 4)
-    '\u0647': 'h'  # ه  (see note 5)
-    '\u064A': 'y'  # ي
-
-    # VOWELS
-    '\u0647\b': 'e' # See notes 1 and 5
-    '\u06D5': 'e' # See notes 1 and 5
-    '\u0626\u06D5': 'e' # See notes 1 and 5
-    '\u0627': 'a' # See note 1
-    '\u0626\u0627': 'a' # See note 1
-    '\u064A': 'î' # See notes 1, 6 and 7
-    '\u0626\u064A': 'î' # See notes 1, 6 and 7
-    '\u0626': 'i'
-    '\u06CE': 'ê' # See note 7
-    '\u0626\u06CE': 'ê' # See note 7
-    '\u0648': 'u'
-    '\u0626\u0648': 'u'
-    '\u0648\u0648': 'û' # See note 7
-    '\u0626\u0648\u0648': 'û' # See note 7
-    '\u06C6': 'o'
-    '\u0626\u06C6': 'o'
-    '\u0648': 'ö' # Rare; previously written وي . See note 7
-    '\u06CA': 'ü' # Only appearing in some dialects and only in old sources. Often equated to /û/ (row 7 above). Sometimes written يو See note 7.