interscript-maps 2.4.3 → 2.5.0

data/maps/odni-kor-Hang-Latn-2015.isc

@@ -0,0 +1,321 @@
+system "ODNI:kor-Hang:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:kor
+  source_script Hang
+  destination_script Latn
+  name ICS-630-01 Romanization of Korean Personal Names (2015)
+  source ICS-630-01 Annex W
+  creation_date 2015
+  adoption_date 
+  description 
+
+  notes {
+    note "    1.  Name order shall be Family Name Given name, with the family name separated\n        from the given name by one space, and the first and second syllable of a two-\n        syllable given name connected by a hyphen. The initial letter of the family name\n        and the initial letter of the first syllable of the given name are capitalized; the\n        second syllable of the given name is in lower case: Kim Yo’ng-su.\n\n    2.  In the case of a full name with only two syllables, the initial letters of both\n        syllables are capitalized and the two names are separated by a space: Ho’ Tam.\n\n        In the case of family names consisting of a combination of two syllables, the\n        syllables are written together (i.e., without a space): So’nu Hak-wo’n.\n\n    3.  The family surname 이 will be rendered \"Yi\" in the IC Standard spelling, but in\n        accordance with personal preference or official usage in the Factbook and Chiefs\n        of State directory.\n\n    4.  In order to facilitate the use of the IC Standard, a reference guide containing a list\n        of syllables used in Korean personal names along with their IC Standard\n        equivalents follows."
+  }
+}
+
+tests {
+   "김영수" ->  "Kim Yo’ng-su"
+   "허담" ->  "Ho’ Tam"
+   "선우학원" ->  "So’nu Hak-wo’n"
+   "이담" ->  "Yi Tam"
+  # examples testing space handling
+   "동방국" ->  "Tongpang Kuk"
+   "동 방국" ->  "Tong Pang-kuk"
+   "동방 국" ->  "Tongpang Kuk"
+   "화방국" ->  "Hwa Pang-kuk"
+   "황목국" ->  "Hwangmok Kuk"
+}
+
+dependency "unicode"
+dependency "var-kor-Hang-Hang-jamo" as hanghang
+
+aliases {
+
+  alpha_plus = any("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ’")
+}
+
+stage main {
+
+
+  # RULES
+  sub {
+    from any([line_start + " ", " " + line_end])
+    to ""
+  }
+
+  #sub some(" "), " "
+
+  # 2 character inputs will have a space between them
+  sub {
+    from line_start + capture(unicode_hangul) + capture(unicode_hangul) + line_end
+    to ref( 1 ) + " " + ref( 2 )
+  }
+
+  # 4 character inputs will have a space as in XXXX -> XX XX
+  sub {
+    from line_start + capture(unicode_hangul + unicode_hangul) + capture(unicode_hangul + unicode_hangul) + line_end
+    to ref( 1 ) + " " + ref( 2 )
+  }
+
+  # 3 character inputs are more complicated. We enumerate all possible 2
+  # letter surnames according to: https://en.wikipedia.org/wiki/List_of_Korean_surnames
+  sub {
+    from line_start + capture(any(["독고", "동방", "등정", "망절", "무본", "부여", "사공", "서문", "선우", "어금", "제갈", "황목", "황보"])) + capture(unicode_hangul) + line_end
+    to ref( 1 ) + " " + ref( 2 )
+  }
+
+  # Otherwise the first character is probably a surname
+  sub {
+    from line_start + capture(unicode_hangul) + capture(unicode_hangul + unicode_hangul) + line_end
+    to ref( 1 ) + " " + ref( 2 )
+  }
+
+  # In case of uncertainity, user needs to add a space himself.
+
+  #sub some(" "), " "
+
+  sub {
+    from any([line_start + " ", " " + line_end])
+    to ""
+  }
+
+
+
+  run  map.hanghang.stage.main
+
+
+  # CHARACTERS
+  parallel {
+    # This is based on Jamo
+
+  }
+
+  # DICTIONARY
+  parallel {
+    #
+  }
+
+
+
+
+  # POSTRULES
+
+  # HANGUL JONGSEONG SSANGKIYEOK
+  sub "ᆩ" "kk"
+
+  # HANGUL JONGSEONG SSANGKIYEOK
+  sub "ᆪ" "ks"
+
+  # HANGUL JONGSEONG NIEUN-CIEUC
+  sub "ᆬ" "nch"
+
+  # HANGUL JONGSEONG NIEUN-CIEUC
+  sub "ᆭ" "nh"
+
+  # HANGUL JONGSEONG TIEUT
+  sub "ᆮ" "t"
+
+  # HANGUL JONGSEONG RIEUL-SIOS
+  sub "ᆳ" "l"
+
+  # HANGUL JONGSEONG RIEUL-THIEUTH
+  sub "ᆴ" "lt’"
+
+  # HANGUL JONGSEONG RIEUL-PHIEUPH
+  sub "ᆵ" "lp’"
+
+  # HANGUL JONGSEONG RIEUL-HIEUH
+  sub "ᆶ" "lh"
+
+  # HANGUL JONGSEONG PIEUP-SIOS
+  sub "ᆹ" "ps"
+
+  # HANGUL JONGSEONG SSANG-SIOS
+  sub "ᆻ" "ss"
+
+  # HANGUL JONGSEONG CIEUC
+  sub "ᆽ" "ch"
+
+  # HANGUL JONGSEONG CHIEUCH
+  sub "ᆾ" "ch’"
+
+  # HANGUL JONGSEONG KHIEUKH
+  sub "ᆿ" "k’"
+
+  # HANGUL JONGSEONG THIEUTH
+  sub "ᇀ" "t’"
+
+  # HANGUL JONGSEONG PHIEUPH
+  sub "ᇁ" "p’"
+
+  # HANGUL JONGSEONG HIEUH
+  sub "ᇂ" "h"
+
+  # HANGUL JONGSEONG KIYEOK
+  sub "ᆨ" "k"
+
+  # HANGUL JONGSEONG NIEUN
+  sub "ᆫ" "n"
+
+  # HANGUL JONGSEONG RIEUL
+  sub "ᆯ" "l"
+
+  # HANGUL JONGSEONG MIEUM
+  sub "ᆷ" "m"
+
+  # HANGUL JONGSEONG PIEUP
+  sub "ᆸ" "p"
+
+  # HANGUL JONGSEONG SIOS
+  sub "ᆺ" "s"
+
+  # HANGUL JONGSEONG IEUNG
+  sub "ᆼ" "ng"
+
+  # HANGUL JONGSEONG RIEUL-KIYEOK
+  sub "ᆰ" "lk"
+
+  # HANGUL JONGSEONG RIEUL-PIEUP
+  sub "ᆲ" "lp"
+
+  # HANGUL CHOSEONG KIYEOK
+  sub "ᄀ" "-k"
+
+  # HANGUL CHOSEONG NIEUN
+  sub "ᄂ" "-n"
+
+  # HANGUL CHOSEONG TIEUT
+  sub "ᄃ" "-t"
+
+  # HANGUL CHOSEONG RIEUL
+  sub "ᄅ" "-r"
+
+  # HANGUL CHOSEONG MIEUM
+  sub "ᄆ" "-m"
+
+  # HANGUL CHOSEONG PIEUP
+  sub "ᄇ" "-p"
+
+  # HANGUL CHOSEONG SIOS
+  sub "ᄉ" "-s"
+
+  # HANGUL CHOSEONG IEUNG
+  sub "ᄋ" "-"
+
+  # HANGUL CHOSEONG CIEUC
+  sub "ᄌ" "-ch"
+
+  # HANGUL CHOSEONG CHIEUCH
+  sub "ᄎ" "-ch’"
+
+  # HANGUL CHOSEONG KHIEUKH
+  sub "ᄏ" "-k’"
+
+  # HANGUL CHOSEONG THIEUTH
+  sub "ᄐ" "-t’"
+
+  # HANGUL CHOSEONG PHIEUPH
+  sub "ᄑ" "-p’"
+
+  # HANGUL CHOSEONG HIEUH
+  sub "ᄒ" "-h"
+
+  # HANGUL CHOSEONG SSANGKIYEOK
+  sub "ᄁ" "-kk"
+
+  # HANGUL CHOSEONG SIOS-KIYEOK
+  sub "ᄭ" "-sk"
+
+  # HANGUL CHOSEONG SSANGTIEUT
+  sub "ᄄ" "-tt"
+
+  # HANGUL CHOSEONG SIOS-TIEUT
+  sub "ᄯ" "-st"
+
+  # HANGUL CHOSEONG SSANGPIEUP
+  sub "ᄈ" "-pp"
+
+  # HANGUL CHOSEONG SIOS-PIEUP
+  sub "ᄲ" "-sp"
+
+  # HANGUL CHOSEONG SSANGSIOS
+  sub "ᄊ" "-ss"
+
+  # HANGUL CHOSEONG SSANGCIEUC
+  sub "ᄍ" "-chch"
+
+  # HANGUL CHOSEONG SIOS-CIEUC
+  sub "ᄶ" "-sch"
+
+  ## End of Choseong Jamos
+
+  # HANGUL JUNGSEONG A
+  sub "ᅡ" "a"
+  # HANGUL JUNGSEONG YA
+  sub "ᅣ" "ya"
+  # HANGUL JUNGSEONG EO
+  sub "ᅥ" "o’"
+  # HANGUL JUNGSEONG YEO
+  sub "ᅧ" "yo’"
+  # HANGUL JUNGSEONG O
+  sub "ᅩ" "o"
+  # HANGUL JUNGSEONG YO
+  sub "ᅭ" "yo"
+  # HANGUL JUNGSEONG U
+  sub "ᅮ" "u"
+  # HANGUL JUNGSEONG YU
+  sub "ᅲ" "yu"
+  # HANGUL JUNGSEONG EU
+  sub "ᅳ" "u’"
+  # HANGUL JUNGSEONG I
+  sub "ᅵ" "i"
+  # HANGUL JUNGSEONG AE
+  sub "ᅢ" "ae"
+  # HANGUL JUNGSEONG YAE
+  sub "ᅤ" "yae"
+  # HANGUL JUNGSEONG E
+  sub "ᅦ" "e"
+  # HANGUL JUNGSEONG YE  # Not found in specification
+  sub "ᅨ" "ye"
+  # HANGUL JUNGSEONG WA
+  sub "ᅪ" "wa"
+  # HANGUL JUNGSEONG WAE
+  sub "ᅫ" "wae"
+  # HANGUL JUNGSEONG OE
+  sub "ᅬ" "oe"
+  # HANGUL JUNGSEONG WE
+  sub "ᅰ" "we"
+  # HANGUL JUNGSEONG WEO
+  sub "ᅯ" "wo’"
+  # HANGUL JUNGSEONG WI
+  sub "ᅱ" "wi"
+  # HANGUL JUNGSEONG YI
+  sub "ᅴ" "ui"
+
+  # Remove before the first syllable dash
+  sub {
+    from "-"
+    to ""
+    before any([line_start, " "])
+  }
+
+  # Remove dash in surname
+  sub {
+    from line_start + capture(some(alpha_plus)) + "-" + capture(some(alpha_plus))
+    to ref( 1 ) + ref( 2 )
+  }
+
+  # Change the surname I to Yi
+  sub {
+    from line_start + "i"
+    to "yi"
+  }
+
+
+  title_case
+}
+}

data/maps/odni-mkd-Cyrl-Latn-2005.isc

@@ -0,0 +1,31 @@
+system "ODNI:mkd-Cyrl:Latn:2005" {
+
+metadata {
+  authority_id odni
+  id 2005
+  language iso-639-2:mkd
+  source_script Cyrl
+  destination_script Latn
+  name Intelligence Community (IC) Standard for the Transliteration of Macedonian Personal Names (2005)
+  creation_date 2005
+  confirmation_date 2005
+  description {    Office of the Director Of National Intelligence Macedonian Personal Names 2004 System
+  }
+}
+
+tests {
+   "Билјана" ->  "Biljana"
+   "Душко" ->  "Dushko"
+}
+
+dependency "odni-mkd-Cyrl-Latn-2015" as cyrllatn
+
+stage main {
+
+  run  map.cyrllatn.stage.main
+
+  # RULES
+
+}
+
+}

data/maps/{odni-mkd-Cyrl-Latn-2015.imp → odni-mkd-Cyrl-Latn-2015.isc}

@@ -1,15 +1,16 @@
+system "ODNI:mkd-Cyrl:Latn:2015" {
+
 metadata {
-  authority_id: odni
-  id: 2015
-  language: iso-639-2:mkd
-  source_script: Cyrl
-  destination_script: Latn
-  name: ICS-630-01 Romanization of Macedonian Personal Names (2015)
-  source: ICS-630-01 Annex H
-  creation_date: 2015
-  confirmation_date: 2015
-  description: |
-    This system is the Intelligence Community (IC) standard for the transliteration of Macedonian
+  authority_id odni
+  id 2015
+  language iso-639-2:mkd
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Macedonian Personal Names (2015)
+  source ICS-630-01 Annex H
+  creation_date 2015
+  confirmation_date 2015
+  description {    This system is the Intelligence Community (IC) standard for the transliteration of Macedonian
     names that will be applied to all final written reports and products for IC consumers. It is not
     intended to eliminate variations of a name that can contribute forensic information. Rather, it is
     to provide an IC standard Romanized (English) transliteration from Macedonian that can then be
@@ -43,82 +44,84 @@ metadata {
     individual is provided, the referent will be clearly identified. This system will be used in
     conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
     names of well-known individuals.
+  }
 }
 
 tests {
-  test "Билјана", "Biljana"
-  test "Душко", "Dushko"
+   "Билјана" ->  "Biljana"
+   "Душко" ->  "Dushko"
 }
 
-stage {
+stage main {
   parallel {
     # RULES
-    sub "\u0053", "Dz" # S => Dz
-    sub "\u0073", "dz" # s => dz
+    sub "\u0053" "Dz"
+    sub "\u0073" "dz"
 
     # CHARACTERS
-    sub "\u0410", "A" # А
-    sub "\u0411", "B" # Б
-    sub "\u0412", "V" # В
-    sub "\u0413", "G" # Г
-    sub "\u0414", "D" # Д
-    sub "\u0403", "Gj" # Ѓ
-    sub "\u0415", "E" # Е
-    sub "\u0416", "Zh" # Ж
-    sub "\u0417", "Z" # З
-    sub "\u0418", "I" # И
-    sub "\u0408", "J" # Ј
-    sub "\u041A", "K" # К
-    sub "\u041B", "L" # Л
-    sub "\u0409", "Lj" # Љ
-    sub "\u041C", "M" # М
-    sub "\u041D", "N" # Н
-    sub "\u040A", "Nj" # Њ
-    sub "\u041E", "O" # О
-    sub "\u041F", "P" # П
-    sub "\u0420", "R" # Р
-    sub "\u0421", "S" # С
-    sub "\u0422", "T" # Т
-    sub "\u040C", "Kj" # Ќ
-    sub "\u0423", "U" # У
-    sub "\u0424", "F" # Ф
-    sub "\u0425", "H" # Х
-    sub "\u0426", "Ts" # Ц
-    sub "\u0427", "Ch" # Ч
-    sub "\u040F", "Dzh" # Џ
-    sub "\u0428", "Sh" # Ш
-    sub "\u2019", "" # ’
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0414" "D"
+    sub "\u0403" "Gj"
+    sub "\u0415" "E"
+    sub "\u0416" "Zh"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0408" "J"
+    sub "\u041A" "K"
+    sub "\u041B" "L"
+    sub "\u0409" "Lj"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u040A" "Nj"
+    sub "\u041E" "O"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u040C" "Kj"
+    sub "\u0423" "U"
+    sub "\u0424" "F"
+    sub "\u0425" "H"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ch"
+    sub "\u040F" "Dzh"
+    sub "\u0428" "Sh"
+    sub "\u2019" ""
 
-    sub "\u0430", "a" # а
-    sub "\u0431", "b" # б
-    sub "\u0432", "v" # в
-    sub "\u0433", "g" # г
-    sub "\u0434", "d" # д
-    sub "\u0453", "gj" # ѓ
-    sub "\u0435", "e" # e
-    sub "\u0436", "zh" # ж
-    sub "\u0437", "z" # з
-    sub "\u0438", "i" # и
-    sub "\u0458", "j" # ј
-    sub "\u043A", "k" # к
-    sub "\u043B", "l" # л
-    sub "\u0459", "lj" # љ
-    sub "\u043C", "m" # м
-    sub "\u043D", "n" # н
-    sub "\u045A", "nj" # њ
-    sub "\u043E", "o" # о
-    sub "\u043F", "p" # п
-    sub "\u0440", "r" # р
-    sub "\u0441", "s" # с
-    sub "\u0442", "t" # т
-    sub "\u045C", "kj" # ќ
-    sub "\u0443", "u" # у
-    sub "\u0444", "f" # ф
-    sub "\u0445", "h" # х
-    sub "\u0446", "ts" # ц
-    sub "\u0447", "ch" # ч
-    sub "\u045F", "dzh" # џ
-    sub "\u0448", "sh" # ш
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0434" "d"
+    sub "\u0453" "gj"
+    sub "\u0435" "e"
+    sub "\u0436" "zh"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0458" "j"
+    sub "\u043A" "k"
+    sub "\u043B" "l"
+    sub "\u0459" "lj"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u045A" "nj"
+    sub "\u043E" "o"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u045C" "kj"
+    sub "\u0443" "u"
+    sub "\u0444" "f"
+    sub "\u0445" "h"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u045F" "dzh"
+    sub "\u0448" "sh"
   }
 
 }
+}

data/maps/odni-prs-Arab-Latn-2004.isc

@@ -0,0 +1,88 @@
+system "ODNI:prs-Arab:Latn:2004" {
+
+metadata {
+  authority_id odni
+  id 2004
+  language iso-639-3:prs
+  source_script Arab
+  destination_script Latn
+  name Intelligence Community (IC) Standard for the Transliteration of Dari Personal Names (2004)
+  creation_date 2004
+  confirmation_date 2004-11
+  description {
+  }
+  notes {
+    note "This standard is intended only for those Afghan names\n that have a common bond or similarity with Iranian or\n Arabic names.  They should not, for example, be used for\n Pashto names, for which a separate standard should be used."
+    note "Long/short vowels:- There is no distinction made in Roman\n between long and short a:-  E.g., Farhad (first a is short,\n second is long)."
+    note "Double consonants:-  Double consonants represented by the\n tashdid are shown by doubling the Roman letter:-  Mohammad.\n Exceptions:-  Consonants represented by Roman digraphs (\n e.g., sh, ch) are not doubled:-  Mobasher [not:-  Mobashsher]\n .  Double letters are only used for tashdid (thus, Hosein [\n not Hossein]) or to reflect the ‘sun letter’ assimilation (\n see below)."
+    note "Hamzeh:-  The hamzeh is represented name-internally by an\n apostrophe, as is the ain.  Name-initially, however,\n neither hamzeh nor ain are indicated in transliteration (\n e.g., Abdorrahman, not 'Abdorrahman)."
+    note "Digraphs:-  No distinction is drawn in Roman between\n digraphs such as sh and single contiguous letters (e.g., s\n followed by h)."
+    note "Arabic definite article \"al\" ('the'):-  Common in many\n names borrowed from Arabic, the transliteration should show\n the 'sun letter' assimilation rather than the “l” for the\n lam.  That  is:-  Abdorrahman.  Note also that the \"Abdol +\n attribute of Allah\" names are written as one unanalyzed\n word, as are other names that contain the definite\n article:-  Shamsoddin (not Shams al-Din), Nezamoddin, etc."
+    note "Diphthongs:-  Diphthongs are written ei and ow\n respectively:-  Hosein; Khosrow."
+    note "Yeh maqsura (final yeh pronounced as “a”):-  should be\n written as “a” as in “Musa”."
+
+    note "Special Rules"
+
+    note "Hyphens:-  A hyphen is used to indicate the ezafeh\n construction:-  Arshad-e Ameri"
+    note "Borrowed names that incorporate the name of God (Allah)\n are transliterated as one word, with the letter \"o\":-  E.g.,\n Abdollah, Ayatollah, Azizollah."
+    note "Foreign names borrowed or appearing in Dari are spelled\n according to the standard Western tradition (even if there\n is an Arabic or Dari version of the same name):-  Joseph,\n Michael."
+    note "Common suffixes, such as gol, pur, mand, yar, zadeh,\n etc., as well as nesbeh (‘relationship’ (to place of birth,\n etc.)) names derived with these suffixes  (e.g., abadi) are\n written as part of the name:-\n gol		Parigol, Ziagol\n pur		Shahpur, Mehrpur\n mand		Gulahmand\n yar		Aminyar\n zadeh		Ismailzadeh, Karimzadeh\n abadi		Kamalabadi"
+  }
+}
+
+tests {
+   "مُوسَى" ->  "musa"
+   "مُؤمِن" ->  "momen"
+   "رِضايي" ->  "rezai"
+   "مُبَشِّر" ->  "mobasher"
+   "حَسَّان" ->  "hassan"
+   "حَسَن" ->  "hasan"
+   "صَفَّار" ->  "saffar"
+   "صَفَر" ->  "safar"
+}
+
+dependency "odni-fas-Arab-Latn-2004" as arablatn
+
+stage main {
+
+
+  # CHARACTERS
+  parallel {
+s
+    sub "\u0626" ""
+    sub "\u0624" ""
+
+    # shadda
+
+    sub "\u0642\u0651" "qq"
+    sub "\u0648\u0651" "ww"
+
+    sub "\u0621" ""
+
+    # FROM NOTES
+
+    sub "\u064a\u064a" "i"
+    sub "\u06cc\u06cc" "i"
+
+    sub {
+    from "\u0627\u064a" + boundary
+    to "i"
+  }
+    sub {
+    from "\u0627\u06cc" + boundary
+    to "i"
+  }
+
+    sub "\u064f\u0648" "u"
+
+    # Farsi consonant characters
+
+    sub "\u0639" ""
+    sub "\u0642" "q"
+    sub "\u0648" "w"
+  }
+
+  run  map.arablatn.stage.main
+}
+
+}