interscript 0.1.2 → 0.1.7

data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml

@@ -0,0 +1,119 @@
+---
+authority_id: bgnpcgn
+id: 1952
+language: iso-639-2:bul
+source_script: Cyrl
+destination_script: Latn
+name: ROMANIZATION SYSTEM FOR BULGARIAN BGN/PCGN of 1952
+alias:
+  ogc11122:
+    code: bul_Cyrl2Latn_BGN_1952
+    description: Bulgarian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) Bulgarian 1952 System
+url: https://libraries.ucsd.edu/bib/fed/USBGN_romanization.pdf
+creation_date: 1945
+confirmation_date: 1952
+description: |
+  This system was adopted by the BGN in 1949 and by the PCGN in 1952. It
+  reflects the much simplified Bulgarian orthography as officially revised in
+  February 1945. The Bulgarian alphabet contains all of the characters present
+  in the Russian alphabet with the exception of ё, ы, and э. Notes 1, 2, and 3
+  are applicable to sources predating the orthographic reform of 1945.
+
+notes:
+  - In modern Bulgarian orthography, the character ъ, does not occcur in word-final position. It should be omitted in romanization when found in word-final position on older sources
+  - The obsolete character ѫ, which was replaced by ъ in 1945, should be romanized ŭ
+  - The obsolete character ѣ, replaced in 1945 by е or я according to local pronunciation, should be romanized as e or ya, accordingly, if the pronunciation is known; otherwise, as ye
+  - The character sequence тс may be romanized t·s in order to differentiate that romanization from the regularly occurring digraph ts, which represents the character ц
+
+tests:
+  - source: София
+    expected: Sofiya
+  - source: София-Град
+    expected: Sofiya-Grad
+  - source: България
+    expected: "Bu\u0306lgariya"
+
+map:
+  rules:
+    # note[1]
+    - pattern: (?<=)\u042a(?=\b)
+      result: ""
+    - pattern: (?<=)\u044a(?=\b)
+      result: ""
+    # note[4]
+    - pattern: "\u0422\u0421"
+      result: T·S
+    - pattern: "\u0422\u0441"
+      result: T·s
+    - pattern: "\u0442\u0441"
+      result: t·s
+
+  characters:
+    '\u0410': 'A'
+    '\u0411': 'B'
+    '\u0412': 'V'
+    '\u0413': 'G'
+    '\u0414': 'D'
+    '\u0415': 'E'
+    '\u0416': 'Zh'
+    '\u0417': 'Z'
+    '\u0418': 'I'
+    '\u0419': 'Y'
+    '\u041a': 'K'
+    '\u041b': 'L'
+    '\u041c': 'M'
+    '\u041d': 'N'
+    '\u041e': 'O'
+    '\u041f': 'P'
+    '\u0420': 'R'
+    '\u0421': 'S'
+    '\u0422': 'T'
+    '\u0423': 'U'
+    '\u0424': 'F'
+    '\u0425': 'Kh'
+    '\u0426': 'Ts'
+    '\u0427': 'Ch'
+    '\u0428': 'Sh'
+    '\u0429': 'St'
+    '\u042a': "U\u0306"
+    '\u042c': "\\'"
+    '\u042e': 'Yu'
+    '\u042f': 'Ya'
+    '\u0430': 'a'
+    '\u0431': 'b'
+    '\u0432': 'v'
+    '\u0433': 'g'
+    '\u0434': 'd'
+    '\u0435': 'e'
+    '\u0436': 'zh'
+    '\u0437': 'z'
+    '\u0438': 'i'
+    '\u0439': 'y'
+    '\u043a': 'k'
+    '\u043b': 'l'
+    '\u043c': 'm'
+    '\u043d': 'n'
+    '\u043e': 'o'
+    '\u043f': 'p'
+    '\u0440': 'r'
+    '\u0441': 's'
+    '\u0442': 't'
+    '\u0443': 'u'
+    '\u0444': 'f'
+    '\u0445': 'kh'
+    '\u0446': 'ts'
+    '\u0447': 'ch'
+    '\u0448': 'sh'
+    '\u0449': 'sht'
+    '\u044a': "u\u0306"
+    '\u044c': "\\'"
+    '\u044e': 'yu'
+    '\u044f': 'ya'
+
+    # note 2
+    '\u046A': "U\u0306" # Ѫ
+    '\u046B': "u\u0306" # ѫ
+
+    # note[3]
+    '\u0462': "Ye" # Ѣ
+    '\u0463': "ye" # ѣ

data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 2013
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: BGN/PCGN 2013 Agreement
+alias:
+  ogc11122:
+    code: bul_Cyrl2Latn_BGN_2013
+    description: Bulgarian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names(PCGN) Bulgarian 2013 System
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811509/ROMANIZATION_OF_BULGARIAN.pdf
 creation_date: 2013
 confirmation date: 2019-06
@@ -15,9 +19,9 @@ description: |
 
 notes:
   - When in final position, “ия” is romanized as “ia” (e.g., София = Sofia; София-Град= Sofia-Grad).
-  - An exception to the romanization system is allowed for the name of the state. Thus, България is roman-
-ized as Bulgaria.
+  - An exception to the romanization system is allowed for the name of the state. Thus, България is romanized as Bulgaria.
   - The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used.
+
 tests:
   - source: София
     expected: Sofia
@@ -27,66 +31,12 @@ tests:
     expected: Bulgaria
 
 map:
-  characters:
-    'България': 'Bulgaria'
-    '\u0410': 'A'
-    '\u0411': 'B'
-    '\u0412': 'V'
-    '\u0413': 'G'
-    '\u0414': 'D'
-    '\u0415': 'E'
-    '\u0416': 'ZH'
-    '\u0417': 'Z'
-    '\u0418': 'I'
-    '\u0419': 'Y'
-    '\u041a': 'K'
-    '\u041b': 'L'
-    '\u041c': 'M'
-    '\u041d': 'N'
-    '\u041e': 'O'
-    '\u041f': 'P'
-    '\u0420': 'R'
-    '\u0421': 'S'
-    '\u0422': 'T'
-    '\u0423': 'U'
-    '\u0424': 'F'
-    '\u0425': 'KH'
-    '\u0426': 'TS'
-    '\u0427': 'CH'
-    '\u0428': 'SH'
-    '\u0429': 'SHT'
-    '\u042a': '\u016c'
-    '\u042c': "\'"
-    '\u042e': 'YU'
-    '\u042f': 'YA'
-    '\u0430': 'a'
-    '\u0431': 'b'
-    '\u0432': 'v'
-    '\u0433': 'g'
-    '\u0434': 'd'
-    '\u0435': 'e'
-    '\u0436': 'zh'
-    '\u0437': 'z'
-    '\u0438': 'i'
-    '\u0439': 'y'
-    '\u043a': 'k'
-    '\u043b': 'l'
-    '\u043c': 'm'
-    '\u043d': 'n'
-    '\u043e': 'o'
-    '\u043f': 'p'
-    '\u0440': 'r'
-    '\u0441': 's'
-    '\u0442': 't'
-    '\u0443': 'u'
-    '\u0444': 'f'
-    '\u0445': 'kh'
-    '\u0446': 'ts'
-    '\u0447': 'ch'
-    '\u0448': 'sh'
-    '\u0449': 'sht'
-    '\u044a': '\u016d'
-    '\u044c': "\'"
-    '\u044e': 'yu'
-    '\u044f': 'ya'
+  inherit: bgnpcgn-bul-Cyrl-Latn-1952
 
+  rules:
+    - pattern: България
+      result: Bulgaria
+    - pattern: (?<=\u0418)\u042f(?=\b) # final position, “ИЯ” is romanized as “IA”
+      result: A
+    - pattern: (?<=\u0438)\u044f(?=\b) # final position, “ия” is romanized as “ia”
+      result: a

data/maps/bgnpcgn-che-Cyrl-Latn-2008.yaml

@@ -0,0 +1,184 @@
+---
+authority_id: bgnpcgn
+id: 2008
+language: iso-639-2:che
+source_script: Cyrl
+destination_script: Latn
+name: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
+creation_date: 2008
+confirmation_date: 2019-07
+description: |
+  Chechen is an official language within Chechnya, one of the republics of the Russian Federation.
+  It will normally be encountered in Cyrillic script, in which case it should be romanized by means of
+  the Cyrillic-Roman table of correspondences given below.
+
+notes:
+  - The letter ə is used to represent short a; a is used for long a.
+  - Ye is used word- and syllable-initially. This Cyrillic letter may be encountered as the ligature ie in Chechen-Roman sources.
+  - This character occurs only in loan words.
+  - q in the combination ккх (qq) and q̇in the combination ккъ (q̇q̇)
+  - ŋ when preceding vowel is nasalized.
+  - This Cyrillic letter may be encountered as the ligature ꭣ [U+AB63] or the diphthong oa in Chechen Roman sources.
+  - Unless in the combinations гӀ, кӀ, пӀ, тӀ, хӀ, цӀ and чӀ.
+  - |
+    An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the
+    unmodified letters of the basic Roman script is:
+
+    All apostrophes appearing in romanization are U+2019
+
+        Ə (U+018F)       ə (U+0259)
+        Ä (U+00C4)       ä (U+00E4)
+        Ġ (U+0047+0307)  ġ (U+0067+0307)
+        Z̵ (U+005A+0335)  z̵ (U+007A+0335)
+        Q̇ (U+0051+0307)  q̇ (U+0071+0307)
+        Ŋ (U+014A)       ŋ (U+014B)
+        Ö (U+00D6)       ö (U+00F6)
+        Ü (U+00DC)       ü (U+00FC)
+        Ẋ (U+0058+0307)  ẋ (U+0078+0307)
+        Ċ (U+0043+0307)  ċ (U0063+0307)
+        Ç (U+00C7)       ç (U+00E7)
+        Ç̇ (U+00C7+0307)  ç̇ (U+00E7+0307)
+        Ş (U+015E)       ş (U+015F)
+
+  - The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used
+
+tests:
+  - source: кӏант
+    expected: khant
+  - source: зуда
+    expected: zuda
+  - source: пхьагал
+    expected: pẋagal
+  - source: наж
+    expected: naz̵
+  - source: мангал
+    expected: mangal
+  - source: Ӏаж
+    expected: Jaz̵
+  - source: Нохчийн Википеди
+    expected: Noxçiyn Vikipedi
+  - source: сагӏадаккхар
+    expected: saġadaqqar
+  - source: йеза
+    expected: yeza
+  - source: еара
+    expected: yeara
+  - source: елха
+    expected: yelxa
+
+map:
+  rules:
+    # note[2]
+    - pattern: (?<!\b\u2019)\b\u0415 # Е in initial position -> Ye
+      result: Ye
+    - pattern: (?<!\b\u2019)\b\u0435 # е in initial position -> ye
+      result: ye
+    # note[4]
+    - pattern: \u043A\u043A\u0445
+      result: qq
+    - pattern: \u043A\u043A\u042A
+      result: q̇q̇
+    - pattern: \u041A\u041A\u0445
+      result: QQ
+    - pattern: \u041A\u041A\u042A
+      result: Q̇Q̇
+
+  characters:
+    '\u0410'        : ['A', 'Ə']        # А note[1]
+    '\u0410\u044C'  : "A\u0308"         # Аь -> Ä
+    '\u0411'        : 'B'               # Б
+    '\u0412'        : 'V'               # В
+    '\u0413'        : 'G'               # Г
+    '\u0413\u04C0'  : "G\u0307"         # ГӀ -> Ġ
+    '\u0414'        : 'D'               # Д
+    '\u0415'        : 'E'               # Е note[2]
+    '\u0401'        : 'Yo'              # Ё note[3]
+    '\u0416'        : "Z\u0335"         # Ж -> Ƶ
+    '\u0417'        : 'Z'               # З
+    '\u0418'        : 'I'               # И
+    '\u042B'        : 'Y'               # Й
+    '\u041A'        : 'K'               # К note[4]
+    '\u041A\u0445'  : 'Q'               # Кх note[4]
+    '\u041A\u044A'  : "Q\u0307"         # Къ -> Q̇ note[4]
+    '\u041A\u04C0'  : 'Kh'              # КӀ note[4]
+    '\u041B'        : 'L'               # Л
+    '\u041C'        : 'M'               # М
+    '\u041D'        : ['N', 'Ŋ']        # Н note[5]
+    '\u041E'        : 'O'               # О note[6]
+    '\u041E\u044C'  : "O\u0308"         # Оь -> Ö
+    '\u041F'        : 'P'               # П
+    '\u041F\u04C0'  : 'Ph'              # ПӀ
+    '\u0420'        : 'R'               # Р
+    '\u0421'        : 'S'               # С
+    '\u0422'        : 'T'               # Т
+    '\u0422\u04C0'  : 'Th'              # TӀ
+    '\u0423'        : 'U'               # У
+    '\u0423\u044C'  : "U\u0308"         # Уь -> Ü
+    '\u0424'        : 'F'               # Ф
+    '\u0425'        : 'X'               # Х
+    '\u0425\u044C'  : "X\u0307"         # Хь -> Ẋ
+    '\u0425\u04C0'  : "H"               # ХӀ
+    '\u04B8'        : 'C'               # Ц
+    '\u04B8\u04C0'  : "C\u0307"         # ЦӀ -> Ċ
+    '\u0427'        : "C\u0327"         # Ч -> Ç
+    '\u0427\u04C0'  : "\u00C7\u0307"    # ЧӀ -> Ç̇
+    '\u0428'        : "S\u0327"         # Ш -> Ş
+    '\u0429'        : "S\u0327C\u0327"  # Щ -> ŞÇ note[3]
+    '\u042A'        : "’"               # Ъ note[3]
+    '\u042B'        : "Y"               # Ы
+    '\u042C'        : ""                # Ь note[3]
+    '\u042D'        : "E"               # Э
+    '\u042E'        : "Yu"              # Ю
+    '\u042E\u044C'  : "Yu\u0308"        # Юь -> Yü
+    '\u042F'        : "Ya"              # Я
+    '\u042F\u044C'  : "Ya\u0308"        # Яь -> Yä
+    '\u04C0'        : "J"               # Ӏ note[7]
+
+    '\u0430'        : ['a', 'ə']        # а note[1]
+    '\u0430\u044C'  : "a\u0308"         # аь -> ä
+    '\u0431'        : 'b'               # б
+    '\u0432'        : 'v'               # в
+    '\u0433'        : 'g'               # г
+    '\u0433\u04CF'  : "g\u0307"         # гӏ -> ġ
+    '\u0434'        : 'd'               # д
+    '\u0435'        : 'e'               # е note[2]
+    '\u0451'        : 'yo'              # ё note[3]
+    '\u0436'        : "z\u0335"         # ж -> ƶ
+    '\u0437'        : 'z'               # з
+    '\u0438'        : 'i'               # и
+    '\u0439'        : 'y'               # й
+    '\u043A'        : 'k'               # к note[4]
+    '\u043A\u0445'  : 'q'               # кх note[4]
+    '\u043A\u044A'  : "q\u0307"         # къ -> q̇ note[4]
+    '\u043A\u04CF'  : 'kh'              # кӏ note[4]
+    '\u043B'        : 'l'               # л
+    '\u043C'        : 'm'               # м
+    '\u043D'        : ['n', 'ŋ']        # н note[5]
+    '\u043E'        : 'o'               # о note[6]
+    '\u043E\u044C'  : "o\u0308"         # оь -> ö
+    '\u043F'        : 'p'               # п
+    '\u0440'        : 'r'               # р
+    '\u0441'        : 's'               # с
+    '\u0442'        : 't'               # т
+    '\u0442\u04CF'  : 'th'              # тӏ
+    '\u0443'        : 'u'               # у
+    '\u0443\u044C'  : "u\u0308"         # Уь -> ü
+    '\u0444'        : 'f'               # ф
+    '\u0445'        : 'x'               # х
+    '\u0445\u044C'  : "x\u0307"         # хь -> ẋ
+    '\u0445\u04CF'  : "h"               # хӏ
+    '\u04B9'        : 'c'               # ц
+    '\u04B9\u04CF'  : "с\u0307"         # цӏ -> ċ
+    '\u0447'        : "c\u0327"         # ч -> ç
+    '\u0447\u04CF'  : "c\u00E7\u0307"   # чӏ -> ç̇
+    '\u0448'        : "s\u0327"         # ш -> ş
+    '\u0449'        : "s\u0327c\u0327"  # щ -> şç note[3]
+    '\u044A'        : "’"               # ъ note[3]
+    '\u044B'        : "y"               # ы
+    '\u044C'        : ''                # ь note[3]
+    '\u044D'        : "e"               # э
+    '\u044E'        : "yu"              # ю
+    '\u044E'        : "yu\u0308"        # юь -> yü
+    '\u044F'        : "ya"              # я
+    '\u044F'        : "ya\u0308"        # яь -> yä
+    '\u04CF'        : "j"               # ӏ note[7]

data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml

@@ -0,0 +1,705 @@
+---
+authority_id: bgnpcgn
+id: 1962
+language: iso-639-2:ell
+source_script: Grek
+destination_script: Latn
+name: BGN/PCGN 1962 System
+alias:
+  ogc11122:
+    code: ell_Grek2Latn_BGN_1962
+    description: US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) Greek 1962 System (out of date)
+url: https://github.com/riboseinc/interscript/files/4225556/BGN_Romanization_Guide_1962_greek.pdf
+creation_date: 1962
+description: |
+  BGN/PCGN Romanization table for Greek
+
+note:
+  - Original specification is for polytonic Greek; this has been adapted for monotonic Greek
+  - The treatment of έι in https://transliteration.eki.ee/pdf/Greek.pdf is incorrect; although
+    not explicitly discussed in the original specification, έι is phonetically equivalent to
+    έϊ, and is to be transliterated as eï, not í (like εί). The same applies to other diphthongs
+    accented on the first syllable.
+
+tests:
+
+  - source: |
+        Ένα πράμα μόνον με παρακίνησε κι εμένα να γράψω ότι τούτην την πατρίδα την έχομεν όλοι μαζί, και σοφοί κι αμαθείς και πλούσιοι και φτωχοί και πολιτικοί και στρατιωτικοί και οι πλέον μικρότεροι άνθρωποι· όσοι αγωνιστήκαμεν, αναλόγως ο καθείς, έχομεν να ζήσομεν εδώ. Το λοιπόν δουλέψαμεν όλοι μαζί, να την φυλάμεν κι όλοι μαζί και να μην λέγει ούτε ο δυνατός «εγώ» ούτε ο αδύνατος. Ξέρετε πότε να λέγει ο καθείς «εγώ»; Όταν αγωνιστεί μόνος του και φκιάσει ή χαλάσει, να λέγει «εγώ»· όταν όμως αγωνίζονται πολλοί και φκιάνουν, τότε να λένε «εμείς». Είμαστε εις το «εμείς» κι όχι εις το «εγώ». Και εις το εξής να μάθομεν γνώση, αν θέλομεν να φκιάσομεν χωριόν, να ζήσομεν όλοι μαζί.
+
+        Γιάννης Μακρυγιάννης.
+
+    expected: |
+        Éna práma mónon me parakínise ki eména na grápso óti toútin tin patrídha tin ékhomen óloi mazí, kai sofoí ki amathís kai ploúsioi kai ftokhoí kai politikoí kai stratiotikoí kai oi pléon mikróteroi ánthropoi; ósoi agonistíkamen, analógos o kathís, ékhomen na zísomen edhó. To loipón dhoulépsamen óloi mazí, na tin filámen ki óloi mazí kai na min léyi oúte o dhinatós «egó» oúte o adhínatos. Xérete póte na léyi o kathís «egó»? Ótan agonistí mónos tou kai fkiási í khalási, na léyi «egó»; ótan ómos agonízondai polloí kai fkiánoun, tóte na léne «emís». Ímaste is to «emís» ki ókhi is to «egó». Kai is to exís na máthomen gnósi, an thélomen na fkiásomen khorión, na zísomen óloi mazí.
+
+        Yiánnis Makriyiánnis.
+
+
+  - source: ΑΘΗΝΑ
+    expected: ATHINA
+  - source: μπαμπάκι
+    expected: bambáki
+  - source: νταντά
+    expected: dandá
+  - source: γκέγκε
+    expected: génge
+  - source: Γκαμπόν
+    expected: Gambón
+  - source: Μάγχη
+    expected: Mánkhi
+  - source: κογξ
+    expected: konx
+  - source: υιός
+    expected: iós
+  - source: Υιός
+    expected: Iós
+  - source: νεράντζι
+    expected: nerántzi
+  - source: Γοίθιος
+    expected: Goíthios
+  - source: μπέικον
+    expected: béïkon
+  - source: μπέϊκον
+    expected: béïkon
+  - source: βόλεϊ
+    expected: vóleï
+  - source: αθεΐα
+    expected: atheḯa
+  - source: Εϊγιαφιάτλαγιοκουτλ
+    expected: Eïyiafiátlayiokoutl
+  - source: Εΐτζι
+    expected: Eḯtzi
+  - source: Μυρτώο
+    expected: Mirtóö
+  - source: αέρας
+    expected: aë́ras
+  - source: γαυ γαυ
+    expected: gav gav
+  - source: Ταΰγετος
+    expected: Taḯyetos
+  - source: σπρέυ
+    expected: spréi
+
+  - source: Αθήνα
+    expected: Athína
+  - source: Άγιον Όρος
+    expected: Áyion Óros
+  - source: Άγραφα
+    expected: Ágrafa
+  - source: Αγρίνιο
+    expected: Agrínio
+  - source: Αίγινα
+    expected: Aíyina
+  - source: Αίγιο
+    expected: Aíyio
+  - source: Αλεξανδρούπολη
+    expected: Alexandroúpoli
+  - source: Αλεποχώρι
+    expected: Alepokhóri
+  - source: Αμοργός
+    expected: Amorgós
+  - source: Άμφισσα
+    expected: Ámfissa
+  - source: Αράχωβα
+    expected: Arákhova
+  - source: Άργος
+    expected: Árgos
+  - source: Αρκαδία
+    expected: Arkadhía
+  - source: Άρτα
+    expected: Árta
+  - source: Βελούχι
+    expected: Veloúkhi
+  - source: Βέροια
+    expected: Véroia
+  - source: Βοιωτία
+    expected: Voiotía
+  - source: Βόλος
+    expected: Vólos
+  - source: Βόνιτσα
+    expected: Vónitsa
+  - source: Γαλαξίδι
+    expected: Galaxídhi
+  - source: Γαλάτσι
+    expected: Galátsi
+  - source: Γιαννιτσά
+    expected: Yiannitsá
+  - source: Γλυφάδα
+    expected: Glifádha
+  - source: Γρανίτσα
+    expected: Granítsa
+  - source: Γρεβενά
+    expected: Grevená
+  - source: Γύθειο
+    expected: Yíthio
+  - source: Διόνυσος
+    expected: Dhiónisos
+  - source: Δίστομο
+    expected: Dhístomo
+  - source: Δολιανά
+    expected: Dholianá
+  - source: Δράμα
+    expected: Dhráma
+  - source: Δωδεκάνησα
+    expected: Dhodhekánisa
+  - source: Έδεσσα
+    expected: Édhessa
+  - source: Ελευσίνα
+    expected: Elevsína
+  - source: Επίδαυρος
+    expected: Epídhavros
+  - source: Επτάνησα
+    expected: Eptánisa
+  - source: Ερμούπολη
+    expected: Ermoúpoli
+  - source: Εύβοια
+    expected: Évvoia
+  - source: Ζάκυνθος
+    expected: Zákinthos
+  - source: Ήπειρος
+    expected: Ípiros
+  - source: Ηράκλειο
+    expected: Iráklio
+  - source: Θάσος
+    expected: Thásos
+  - source: Θεσσαλονίκη
+    expected: Thessaloníki
+  - source: Θεσσαλία
+    expected: Thessalía
+  - source: Θεσπρωτία
+    expected: Thesprotía
+  - source: Θήβα
+    expected: Thíva
+  - source: Θράκη
+    expected: Thráki
+  - source: Ιθάκη
+    expected: Itháki
+  - source: Ίος
+    expected: Íos
+  - source: Ιωάννινα
+    expected: Ioánnina
+  - source: Καβάλα
+    expected: Kavála
+  - source: Καλάβρυτα
+    expected: Kalávrita
+  - source: Καλαμάτα
+    expected: Kalamáta
+  - source: Καλαμπάκα
+    expected: Kalambáka
+  - source: Καλύβια
+    expected: Kalívia
+  - source: Κάλυμνος
+    expected: Kálimnos
+  - source: Καρδίτσα
+    expected: Kardhítsa
+  - source: Καρπενήσι
+    expected: Karpenísi
+  - source: Κάρυστος
+    expected: Káristos
+  - source: Καστελλόριζο
+    expected: Kastellórizo
+  - source: Καστοριά
+    expected: Kastoriá
+  - source: Κατερίνη
+    expected: Kateríni
+  - source: Κάτω Αχαΐα
+    expected: Káto Akhaḯa
+  - source: Κερατέα
+    expected: Keratéa
+  - source: Κέρκυρα
+    expected: Kérkira
+  - source: Κεφαλλονιά
+    expected: Kefalloniá
+  - source: Κηφισιά
+    expected: Kifisiá
+  - source: Κιλκίς
+    expected: Kilkís
+  - source: Κοζάνη
+    expected: Kozáni
+  - source: Κολωνός
+    expected: Kolonós
+  - source: Κομοτηνή
+    expected: Komotiní
+  - source: Κόρινθος
+    expected: Kórinthos
+  - source: Κορώνη
+    expected: Koróni
+  - source: Κρανίδι
+    expected: Kranídhi
+  - source: Κρέστενα
+    expected: Kréstena
+  - source: Κρήτη
+    expected: Kríti
+  - source: Κύθηρα
+    expected: Kíthira
+  - source: Κυκλάδες
+    expected: Kikládhes
+  - source: Κύμη
+    expected: Kími
+  - source: Κυψέλη
+    expected: Kipséli
+  - source: Κως
+    expected: Kos
+  - source: Λαγκαδάς
+    expected: Langadhás
+  - source: Λαμία
+    expected: Lamía
+  - source: Λάρισα
+    expected: Lárisa
+  - source: Λαύριο
+    expected: Lávrio
+  - source: Λέρος
+    expected: Léros
+  - source: Λέσβος
+    expected: Lésvos
+  - source: Λευκάδα
+    expected: Levkádha
+  - source: Λήμνος
+    expected: Límnos
+  - source: Λιβαδειά
+    expected: Livadhiá
+  - source: Μακεδονία
+    expected: Makedhonía
+  - source: Μάνη
+    expected: Máni
+  - source: Μαραθώνας
+    expected: Marathónas
+  - source: Μαρκόπουλο
+    expected: Markópoulo
+  - source: Μαρούσι
+    expected: Maroúsi
+  - source: Μέγαρα
+    expected: Mégara
+  - source: Μεσολόγγι
+    expected: Mesolóngi
+  - source: Μεταξουργείο
+    expected: Metaxouryío
+  - source: Μέτσοβο
+    expected: Métsovo
+  - source: Μήλος
+    expected: Mílos
+  - source: Μύκονος
+    expected: Míkonos
+  - source: Μυστράς
+    expected: Mistrás
+  - source: Μυτιλήνη
+    expected: Mitilíni
+  - source: Νάξος
+    expected: Náxos
+  - source: Νάουσα
+    expected: Náousa
+  - source: Ναύπακτος
+    expected: Návpaktos
+  - source: Ναύπλιο
+    expected: Návplio
+  - source: Νέα Σμύρνη
+    expected: Néa Smírni
+  - source: Νίσυρος
+    expected: Nísiros
+  - source: Ξάνθη
+    expected: Xánthi
+  - source: Όλυμπος
+    expected: Ólimbos
+  - source: Παγκράτι
+    expected: Pangráti
+  - source: Παπάγου
+    expected: Papágou
+  - source: Πάρος
+    expected: Páros
+  - source: Πασαλιμάνι
+    expected: Pasalimáni
+  - source: Πατήσια
+    expected: Patísia
+  - source: Πάτμος
+    expected: Pátmos
+  - source: Πάτρα
+    expected: Pátra
+  - source: Πειραιάς
+    expected: Piraiás
+  - source: Πελοπόννησος
+    expected: Pelopónnisos
+  - source: Περιστέρι
+    expected: Peristéri
+  - source: Πεύκη
+    expected: Pévki
+  - source: Πήλιο
+    expected: Pílio
+  - source: Πολύγυρος
+    expected: Políyiros
+  - source: Πόρος
+    expected: Póros
+  - source: Πρέβεζα
+    expected: Préveza
+  - source: Πτολεμαΐδα
+    expected: Ptolemaḯdha
+  - source: Πύλος
+    expected: Pílos
+  - source: Πύργος
+    expected: Pírgos
+  - source: Ρέθυμνο
+    expected: Réthimno
+  - source: Ρόδος
+    expected: Ródhos
+  - source: Ρούμελη
+    expected: Roúmeli
+  - source: Σαλαμίνα
+    expected: Salamína
+  - source: Σαμοθράκη
+    expected: Samothráki
+  - source: Σάμος
+    expected: Sámos
+  - source: Σαντορίνη
+    expected: Sandoríni
+  - source: Σέρρες
+    expected: Sérres
+  - source: Σίκινος
+    expected: Síkinos
+  - source: Σίφνος
+    expected: Sífnos
+  - source: Σκιάθος
+    expected: Skiáthos
+  - source: Σκόπελος
+    expected: Skópelos
+  - source: Σούλι
+    expected: Soúli
+  - source: Σπάρτη
+    expected: Spárti
+  - source: Στερεά Ελλάδα
+    expected: Stereá Elládha
+  - source: Στύρα
+    expected: Stíra
+  - source: Σύμη
+    expected: Sími
+  - source: Σύρος
+    expected: Síros
+  - source: Σφακιά
+    expected: Sfakiá
+  - source: Τήλος
+    expected: Tílos
+  - source: Τήνος
+    expected: Tínos
+  - source: Τρίκαλα
+    expected: Tríkala
+  - source: Τρίπολη
+    expected: Trípoli
+  - source: Τσακωνιά
+    expected: Tsakoniá
+  - source: Ύδρα
+    expected: Ídhra
+  - source: Φάληρο
+    expected: Fáliro
+  - source: Φλώρινα
+    expected: Flórina
+  - source: Φολέγανδρος
+    expected: Folégandros
+  - source: Χάλκη
+    expected: Khálki
+  - source: Χαλκίδα
+    expected: Khalkídha
+  - source: Χαλάνδρι
+    expected: Khalándri
+  - source: Χαλκιδική
+    expected: Khalkidhikí
+  - source: Χανιά
+    expected: Khaniá
+  - source: Χίος
+    expected: Khíos
+  - source: Ψαρά
+    expected: Psará
+  - source: Αβάνα
+    expected: Avána
+  - source: Αγγλία
+    expected: Anglía
+  - source: Αϊβαλί
+    expected: Aïvalí
+  - source: Αλεξάνδρεια
+    expected: Alexándria
+  - source: Άμστερνταμ
+    expected: Ámsterndam
+  - source: Βαυαρία
+    expected: Vavaría
+  - source: Βενετία
+    expected: Venetía
+  - source: Βερολίνο
+    expected: Verolíno
+  - source: Βερόνα
+    expected: Veróna
+  - source: Βιέννη
+    expected: Viénni
+  - source: Γένοβα
+    expected: Yénova
+  - source: Δουβλίνο
+    expected: Dhouvlíno
+  - source: Καλαβρία
+    expected: Kalavría
+  - source: Καλιφόρνια
+    expected: Kalifórnia
+  - source: Καύκασος
+    expected: Kávkasos
+  - source: Κονγκό
+    expected: Konngó
+  - source: Κορσική
+    expected: Korsikí
+  - source: Κουρδιστάν
+    expected: Kourdhistán
+  - source: Κωνσταντινούπολη
+    expected: Konstandinoúpoli
+  - source: Κατεχόμενη Κύπρος
+    expected: Katekhómeni Kípros
+  - source: Λαπωνία
+    expected: Laponía
+  - source: Λευκωσία
+    expected: Levkosía
+  - source: Λιβόρνο
+    expected: Livórno
+  - source: Λονδίνο
+    expected: Londhíno
+  - source: Λυών
+    expected: Lión
+  - source: Μάλαγα
+    expected: Málaga
+  - source: Μασσαλία
+    expected: Massalía
+  - source: Μικρονησία
+    expected: Mikronisía
+  - source: Μιλάνο
+    expected: Miláno
+  - source: Μόσχα
+    expected: Móskha
+  - source: Μπολόνια
+    expected: Bolónia
+  - source: Νάπολη
+    expected: Nápoli
+  - source: Νταγκεστάν
+    expected: Dangestán
+  - source: Νέα Υόρκη
+    expected: Néa Iórki
+  - source: Οξφόρδη
+    expected: Oxfórdhi
+  - source: Ουαλία
+    expected: Oualía
+  - source: Παρίσι
+    expected: Parísi
+  - source: Πάφος
+    expected: Páfos
+  - source: Πολυνησία
+    expected: Polinisía
+  - source: Ρώμη
+    expected: Rómi
+  - source: Σαμάρεια
+    expected: Samária
+  - source: Σικελία
+    expected: Sikelía
+  - source: Σκανδιναβία
+    expected: Skandhinavía
+  - source: Σκόπια
+    expected: Skópia
+  - source: Σκωτία
+    expected: Skotía
+  - source: Σμύρνη
+    expected: Smírni
+  - source: Ταϊτή
+    expected: Taïtí
+  - source: Ταταρστάν
+    expected: Tatarstán
+  - source: Τζαμάικα
+    expected: Tzamáika
+  - source: Τηλλυρία
+    expected: Tilliría
+  - source: Τιρόλο
+    expected: Tirólo
+  - source: Τορίνο
+    expected: Toríno
+  - source: Φανάρι
+    expected: Fanári
+  - source: Φλωρεντία
+    expected: Florendía
+  - source: Χαβάη
+    expected: Khaváï
+  - source: Χονγκ Κονγκ
+    expected: Khonng Konng
+
+map:
+  # https://en.wikipedia.org/wiki/Romanization_of_Greek
+  rules:
+    - pattern: (?<=[ΑαΕεΗη])\u03A5    # Υ (after Α, Ε, Η)
+      result: V
+    - pattern: (?<=[ΑαΕεΗη])\u03C5    # υ (after Α, Ε, Η)
+      result: v
+    - pattern: (?<=[Οο])\u03A5    # Υ (after Ο)
+      result: U
+    - pattern: (?<=[Οο])\u03C5    # υ (after Ο)
+      result: u
+    - pattern: (?<=[Οο])\u03CD    # ύ (after Ο)
+      result: ú
+    - pattern: \u03A5[Ιιί]        # ΥΙ
+      result: I
+    - pattern: \u03C5[Ιιί]        # υι
+      result: i
+    - pattern: \u03A5[ί]        # ΥΙ
+      result: Í
+    - pattern: \u03C5[ί]        # υι
+      result: í
+    - pattern: \u0393(?=[ξΞχΧ])    # Γ (before Γ, Ξ, Χ)
+      result: N
+    - pattern: \u03B3(?=[ξΞχΧ])    # γ (before Γ, Ξ, Χ)
+      result: n
+    - pattern: \u0393[Γγ]    # Γ (before Γ, Ξ, Χ)
+      result: Ng
+    - pattern: \u03B3\u03B3    # γ (before Γ, Ξ, Χ)
+      result: ng
+    - pattern: (?<=\b)\u0393[Κκ]    # Γ (before Κ initially)
+      result: G
+    - pattern: (?<=\b)\u03B3[Κκ]    # γ (before Κ initially)
+      result: g
+    - pattern: (?<!\b)\u0393[Κκ]    # Γ (before Κ medially)
+      result: Ng
+    - pattern: (?<!\b)\u03B3[Κκ]    # γ (before Κ medially)
+      result: ng
+    - pattern: \u0393(?=[ΕεέΗηήΙιίΥυύ])    # Γ (before front vowels)
+      result: Y
+    - pattern: \u03B3(?=[ΕεέΗηήΙιίΥυύ])    # γ (before front vowels)
+      result: y
+    - pattern: \u0393(?=[Oo][Ιιί])    # Γ (before front vowels)
+      result: Y
+    - pattern: \u03B3(?=[Oo][Ιιί])    # γ (before front vowels)
+      result: y
+    - pattern: (?<=\b)\u039D[τΤ]    # ΝΤ (initially)
+      result: D
+    - pattern: (?<=\b)\u03BD[τΤ]    # ντ (initially)
+      result: d
+    - pattern: \u039D[τΤ][ζΖ]    # ΝΤΖ
+      result: NTZ
+    - pattern: \u03BD[τΤ][ζΖ]    # ντζ
+      result: ntz
+    - pattern: (?<!\b)\u039D[τΤ]    # ΝΤ (medially)
+      result: Nd
+    - pattern: (?<!\b)\u03BD[τΤ]    # ντ (medially)
+      result: nd
+    - pattern: (?<=\b)\u039C[πΠ]    # ΜΠ (initially)
+      result: B
+    - pattern: (?<=\b)\u03BC[πΠ]    # μπ (initially)
+      result: b
+    - pattern: \u039C[πΠ]    # ΜΠ (medially)
+      result: Mb
+    - pattern: \u03BC[πΠ]    # μπ (medially)
+      result: mb
+    - pattern: (?<=[νΝ])\u0394(?=[ρΡ])    # νδρ
+      result: d
+    - pattern: (?<=[νΝ])\u03B4(?=[ρΡ])    # νδρ
+      result: d
+    - pattern: (?<=[ΑΆαά])\u0395    # ΑΕ
+      result: Ë
+    - pattern: (?<=[ΑΆαά])\u03B5    # αε
+      result: ë
+    - pattern: (?<=[ΑΆαά])\u03AD    # αέ
+      result: ë́
+    - pattern: (?<=[ΩΏωώ])\u039F    # ΩΟ
+      result: Ö
+    - pattern: (?<=[ΩΏωώ])\u03BF    # ωο
+      result: ö
+    - pattern: (?<=[ΩΏωώ])\u03CC    # ωό
+      result: ö́
+    - pattern: (?<=[ΑΆαάΟΌοό])\u0397    # ΑΗ, ΟΗ
+      result: Ï
+    - pattern: (?<=[ΑΆαάΟΌοό])\u03B7    # αη, οη
+      result: ï
+    - pattern: (?<=[ΑΆαάΟΌοό])\u03AE    # αή, οή
+      result: ḯ
+    - pattern: \u037E   # ;
+      result: "?"
+    - pattern: \u003B   # ;
+      result: "?"
+
+  characters:
+    "\u0027": ""
+    "\u0386": "Á"  # Ά
+    "\u0391": "A"  # Α
+    "\u0392": "V"  # Β
+    "\u0393": "G"  # Γ
+    "\u0394": "Dh"  # Δ
+    "\u0395": "E"  # Ε
+    "\u0395\u0399": "I"  # ΕΙ
+    "\u0395\u03B9": "I"  # Ει
+    "\u0395\u03AF": "Í"  # Εί
+    "\u0395\u03AA": "Εï"  # ΕΪ
+    "\u0395\u03CA": "Εï"  # Εϊ
+    "\u0388\u03CA": "Éï"  # Έϊ
+    "\u0388\u03CA": "Éï"  # Έι
+    "\u0391\u03CD": "Áv"  # Αύ
+    "\u0395\u03CD": "Év"  # Εύ
+    "\u0397\u03CD": "Ív"  # Ηύ
+    "\u0396": "Z"  # Ζ
+    "\u0397": "I"  # Η
+    "\u0398": "Th" # Θ
+    "\u0399": "I"  # Ι
+    "\u039A": "K"  # Κ
+    "\u039B": "L"  # Λ
+    "\u039C": "M"  # Μ
+    "\u039D": "N"  # Ν
+    "\u039E": "X"  # Ξ
+    "\u039F": "O"  # Ο
+    "\u03A0": "P"  # Π
+    "\u03A1": "R"  # Ρ
+    "\u03A3": "S"  # Σ
+    "\u03A4": "T"  # Τ
+    "\u03A5": "I"  # Υ
+    "\u03A6": "F" # Φ
+    "\u03A7": "Kh" # Χ
+    "\u03A8": "Ps" # Ψ
+    "\u03A9": "O"  # Ω
+    "\u0388": "É"  # Έ
+    "\u0389": "Í"  # Ή
+    "\u038A": "Í"  # Ί
+    "\u038C": "Ó"  # Ό
+    "\u038E": "Í"  # Ύ
+    "\u038F": "Ó"  # Ώ
+    "\u03AA": "Ï"  # Ϊ
+    "\u03AB": "Ï"  # Ϋ
+
+    "\u03AC": "á"  # ά
+    "\u03B1": "a"  # α
+    "\u03B2": "v"  # β
+    "\u03B3": "g"  # γ
+    "\u03B4": "dh"  # δ
+    "\u03B5": "e"  # ε
+    "\u03B5\u03B9": "i"  # ει
+    "\u03B5\u03AF": "í"  # εί
+    "\u03B5\u03CA": "eï"  # εϊ
+    "\u03AD\u03CA": "éï"  # έϊ
+    "\u03AD\u03B9": "éï"  # έι
+    "\u03B1\u03CD": "áv"  # αύ
+    "\u03B5\u03CD": "év"  # εύ
+    "\u03B7\u03CD": "ív"  # ηύ
+    "\u03B6": "z"  # ζ
+    "\u03B7": "i"  # η
+    "\u03B8": "th" # θ
+    "\u03B9": "i"  # ι
+    "\u03BA": "k"  # κ
+    "\u03BB": "l"  # λ
+    "\u03BC": "m"  # μ
+    "\u03BD": "n"  # ν
+    "\u03BE": "x"  # ξ
+    "\u03BF": "o"  # ο
+    "\u03C0": "p"  # π
+    "\u03C1": "r"  # ρ
+    "\u03C3": "s"  # σ
+    "\u03C2": "s"  # ς
+    "\u03C4": "t"  # τ
+    "\u03C5": "i"  # υ
+    "\u03C6": "f" # φ
+    "\u03C7": "kh" # χ
+    "\u03C8": "ps" # ψ
+    "\u03C9": "o"  # ω
+    "\u03AD": "é"  # έ
+    "\u03AE": "í"  # ή
+    "\u03AF": "í"  # ί
+    "\u03CC": "ó"  # ό
+    "\u03CD": "í"  # ύ
+    "\u03CE": "ó"  # ώ
+    "\u03CA": "ï"  # ϊ
+    "\u03CB": "ï"  # ϋ
+    "\u0390": "ḯ"  # ΐ
+    "\u03B0": "ḯ"  # ΰ
+
+    "\u0387": ";"   # ·
+    "\u00B7": ";"   # ·