interscript-maps 2.4.3 → 2.5.0

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

@@ -1,110 +0,0 @@
-metadata {
-  authority_id: alalc
-  id: 1997
-  language: iso-639-2:bul
-  source_script: Cyrl
-  destination_script: Latn
-  name: Romanization Table -- Bulgarian (1997)
-  url: http://www.rechtertie.nl/databases/judd/downloads/Bulgarian.pdf
-  creation_date: 1997
-
-  notes:
-    - |
-      The letter Ъ in the initial and medial position is a vowel in Bulgarian and is romanized as ŭ.
-      It appears in the final position chiefly in texts published before 1945, in which it serves as
-      a hard sign and is romanized as ʺ.
-    - The letters Ѣ and Ѫ are found chiefly in texts published before the orthographic reform of 1945.
-}
-
-tests {
-  # missing
-}
-
-# This map has been partially converted by the bin/maps_v1_to_v2 script
-# The section below requires human attention. Remember to remove this
-# comment and move the converted map to 'maps/' directory. Please also
-# take note that the maps-staging directory will be cleaned up whenever
-# you run the bin/maps_v1_to_v2 script. You should particularly be
-# concerned about any regular expressions found in this file and about
-# advanced expressions in parallel {} parts, and also about the order
-# of particular parts of the stage.
-
-stage {
-
-  # RULES
-  # note[1]
-  sub "\u042a", "ʺ", before: "", after: boundary
-  sub "u044a", "ʺ", before: "", after: boundary
-
-
-  # CHARACTERS
-  parallel {
-    sub "\u0410", "A"
-    sub "\u0411", "B"
-    sub "\u0412", "V"
-    sub "\u0413", "G"
-    sub "\u0414", "D"
-    sub "\u0415", "E"
-    sub "\u0416", "Zh"
-    sub "\u0417", "Z"
-    sub "\u0418", "I"
-    sub "\u0419", "Ĭ" # Ĭ
-    sub "\u041a", "K"
-    sub "\u041b", "L"
-    sub "\u041c", "M"
-    sub "\u041d", "N"
-    sub "\u041e", "O"
-    sub "\u041f", "P"
-    sub "\u0420", "R"
-    sub "\u0421", "S"
-    sub "\u0422", "T"
-    sub "\u0423", "U"
-    sub "\u0424", "F"
-    sub "\u0425", "Kh"
-    sub "\u0426", "T͡S"
-    sub "\u0427", "Ch"
-    sub "\u0428", "Sh"
-    sub "\u0429", "Sht"
-    sub "\u042a", "Ŭ" # or ʺ check note[1]
-    sub "\u042c", "\u02B9"
-    sub "\u0462", "I͡E" # Ѣ check note [2]
-    sub "\u042e", "I͡U"
-    sub "\u042f", "I͡A"
-    sub "\u046A", "U̐" # Ѫ check note [2]
-
-    sub "\u0430", "a"
-    sub "\u0431", "b"
-    sub "\u0432", "v"
-    sub "\u0433", "g"
-    sub "\u0434", "d"
-    sub "\u0435", "e"
-    sub "\u0436", "zh"
-    sub "\u0437", "z"
-    sub "\u0438", "i"
-    sub "\u0439", "ĭ" # ĭ
-    sub "\u043a", "k"
-    sub "\u043b", "l"
-    sub "\u043c", "m"
-    sub "\u043d", "n"
-    sub "\u043e", "o"
-    sub "\u043f", "p"
-    sub "\u0440", "r"
-    sub "\u0441", "s"
-    sub "\u0442", "t"
-    sub "\u0443", "u"
-    sub "\u0444", "f"
-    sub "\u0445", "kh"
-    sub "\u0446", "t͡s"
-    sub "\u0447", "ch"
-    sub "\u0448", "sh"
-    sub "\u0449", "sht"
-    sub "\u044a", "ŭ" # or ʺ check note[1]
-    sub "\u044c", "\u02B9"
-    sub "\u0463", "i͡e" # ѣ check note [2]
-    sub "\u044e", "i͡u"
-    sub "\u044f", "i͡a"
-    sub "\u046B", "u̐" # ѫ check note [2]
-  }
-
-}
-

data/maps/alalc-div-Thaa-Latn-1997.imp

@@ -1,171 +0,0 @@
-metadata {
-  authority_id: alalc
-  id: 1997
-  language: iso-639-2:div
-  source_script: Thaa
-  destination_script: Latn
-  name: Romanization Table -- Divehi (1997)
-  url: http://catdir.loc.gov/catdir/cpso/romanization/divehi.pdf
-  creation_date: 1997
-  description: |
-    ALA-Library of Congress Divehi Romanization 1997 System
-
-  notes:
-
-    - |
-      Romanize ށް as ḫ when it doubles the following consonant or is used as a glottal stop.
-        aḫvana	އަށްވަނަ
-        maśaḫ	މަށަށް
-    - |
-      When used in medial position without ް (sukūn), romanize ނ as ṁ.
-        aṁga	އަނގަ
-        haṁdu	ހަނދު
-    - |
-      Romanization of އ.
-      (a) When used in the initial position with any vowel sign, do not romanize.
-        ata	އަތަ
-        idu	އިދު
-        umuru	އުމުރު
-        egahugi	އެގަހުގި
-      (b) When used in the medial position with any vowel sign, romanize as ’.
-        ha’hūnu	ހައިހޫނު
-        fa’isa	ފައިސަ
-        k’īn	ކްއީން
-      (c) When a consonant follows އް in medial position, double it in romanization.
-        cappalu	ޗައްޕަލު
-        appacci	އައްޕައްޗި
-      (d) When used in final position with ް (sukūn), romanize as h.
-        boh	ބޮއް
-        biheh	ބިހެއް
-    - |
-      Romanize ތް followed by another ތ as  t̤ .
-       at̤teri   އަތްތެރި
-    - |
-      Only the vowel forms that appear at the beginning of a syllable are listed.
-      When the vowels follow a consonant, އ is not used and the vowel signs are added to the consonant forms.
-      Do not distinguish between the two in romanization.
-    - |
-      ް (called sukūn) generally indicates omission of an inherent vowel associated with a consonant.
-      For its other uses, see Notes 1, 3, and 4.
-}
-
-tests {
-  test "މަށަށް", "maśaḫ"
-  test "އަނގަ", "aṁga"
-  test "ހަނދު", "haṁdu"
-  test "އަތަ", "ata"
-  test "އިދު", "idu"
-  test "އުމުރު", "umuru"
-  test "އެގަހުގި", "egahugi"
-  test "ފައިސަ", "faʼisa"
-  test "ބޮއް", "boh"
-  test "ބިހެއް", "biheh"
-  test "އަތްތެރި", "at̤teri"
-  test "ޗައްޕަލު", "cappalu"
-  test "އައްޕައްޗި", "appacci"
-}
-
-stage {
-
-  # RULES
-  # note[1]
-  sub "\u0781\u07b0", "ḫ", after: boundary, before: ""
-  # note[2]
-  sub "\u0782\u07b0", "n", not_before: boundary # medial position with sukun
-  sub "\u0782", "ṁ", not_before: boundary # medial position without sukun
-  # note[3(a)]
-  sub boundary + capture("\u0787" + maybe("=")), "", after: any("\u07a6\u07a7\u07a8\u07a9\u07aa\u07ab\u07ac\u07ad\u07ae\u07af") # initial position with any vowel sign
-  # note[3(c)]  a consonant follows އް in medial position
-  sub "\u0787\u07b0", "h", not_before: boundary, after: "ހ"
-  sub "\u0787\u07b0", "ś", not_before: boundary, after: "ށ"
-  sub "\u0787\u07b0", "n", not_before: boundary, after: "ނ"
-  sub "\u0787\u07b0", "r", not_before: boundary, after: "ރ"
-  sub "\u0787\u07b0", "b", not_before: boundary, after: "ބ"
-  sub "\u0787\u07b0", "ḷ", not_before: boundary, after: "ޅ"
-  sub "\u0787\u07b0", "k", not_before: boundary, after: "ކ"
-  sub "\u0787\u07b0", "v", not_before: boundary, after: "ވ"
-  sub "\u0787\u07b0", "m", not_before: boundary, after: "މ"
-  sub "\u0787\u07b0", "f", not_before: boundary, after: "ފ"
-  sub "\u0787\u07b0", "d", not_before: boundary, after: "ދ"
-  sub "\u0787\u07b0", "t", not_before: boundary, after: "ތ"
-  sub "\u0787\u07b0", "l", not_before: boundary, after: "ލ"
-  sub "\u0787\u07b0", "g", not_before: boundary, after: "ގ"
-  sub "\u0787\u07b0", "ñ", not_before: boundary, after: "ޏ"
-  sub "\u0787\u07b0", "s", not_before: boundary, after: "ސ"
-  sub "\u0787\u07b0", "ḍ", not_before: boundary, after: "ޑ"
-  sub "\u0787\u07b0", "j", not_before: boundary, after: "ޖ"
-  sub "\u0787\u07b0", "c", not_before: boundary, after: "ޗ"
-  sub "\u0787\u07b0", "z", not_before: boundary, after: "ޒ"
-  sub "\u0787\u07b0", "ṭ", not_before: boundary, after: "ޓ"
-  sub "\u0787\u07b0", "p", not_before: boundary, after: "ޕ"
-  sub "\u0787\u07b0", "y", not_before: boundary, after: "ޔ"
-  # note[3(d)]
-  sub "\u0787\u07b0", "h", not_before: boundary, after: boundary # final position with sukun
-  # note[3(b)]
-  sub "\u0787", "ʼ", not_before: boundary, after: any("\u07a6\u07a7\u07a8\u07a9\u07aa\u07ab\u07ac\u07ad\u07ae\u07af") # medial position with any vowel sign
-  # note[4]
-  sub "\u078c\u07b0\u078c", "t̤t"
-
-
-
-  # CHARACTERS
-  parallel {
-
-    # Vowels
-
-    sub "ަ", "a"
-    sub "ާ", "ā"
-    sub "ި", "i"
-    sub "ީ", "ī"
-    sub "ު", "u"
-    sub "ޫ", "ū"
-    sub "ެ", "e"
-    sub "ޭ", "ē"
-    sub "ޮ", "o"
-    sub "ޯ", "ō"
-    sub "ް", "" # omit (see Note 6)
-
-
-    # Consonants
-    sub "ހ", "h"
-    sub "ށ", "ś" # or ḫ (see Note 1)
-    sub "ނ", "n" # see Note 2
-    sub "ރ", "r"
-    sub "ބ", "b"
-    sub "ޅ", "ḷ"
-    sub "ކ", "k"
-    sub "އ", "" # ʼ or h or omit (see Note 3)
-    sub "ވ", "v"
-    sub "މ", "m"
-    sub "ފ", "f"
-    sub "ދ", "d"
-    sub "ތ", "t" # see Note 4
-    sub "ލ", "l"
-    sub "ގ", "g"
-    sub "ޏ", "ñ"
-    sub "ސ", "s"
-    sub "ޑ", "ḍ"
-    sub "ޖ", "j"
-    sub "ޗ", "c"
-    sub "ޒ", "z"
-    sub "ޓ", "ṭ"
-    sub "ޕ", "p"
-    sub "ޔ", "y"
-
-    # Divehi Equivalents to Represent Arabic Letters
-
-    sub "ޘ", "th"
-    sub "ޙ", "ḥ"
-    sub "ޚ", "kh"
-    sub "ޛ", "dh"
-    sub "ޝ", "sh"
-    sub "ޞ", "ṣ"
-    sub "ޟ", "ḏ"
-    sub "ޠ", "t̤"
-    sub "ޡ", "ẓ"
-    sub "ޢ", "ʻ"
-    sub "ޣ", "gh"
-    sub "ޤ", "q"
-  }
-
-}

data/maps/alalc-div-Thaa-Latn-2012.imp

@@ -1,74 +0,0 @@
-metadata {
-  authority_id: alalc
-  id: 2012
-  language: iso-639-2:div
-  source_script: Thaa
-  destination_script: Latn
-  name: Romanization Table -- Divehi (2012)
-  url: https://www.loc.gov/catdir/cpso/romanization/divehi.pdf
-  creation_date: 2012
-  description: |
-    ALA-Library of Congress Divehi Romanization 2012 System
-
-  notes:
-
-    - |
-      Romanize ށް as ḫ when it doubles the following consonant or is used as a glottal stop.
-        aḫvana	އަށްވަނަ
-        maśaḫ	މަށަށް
-    - |
-      When used in medial position without ް (sukūn), romanize ނ as ṁ.
-        aṁga	އަނގަ
-        haṁdu	ހަނދު
-    - |
-      Romanization of އ.
-      (a) When used in the initial position with any vowel sign, do not romanize.
-        ata	އަތަ
-        idu	އިދު
-        umuru	އުމުރު
-        egahugi	އެގަހުގި
-      (b) When used in the medial position with any vowel sign, romanize as ’.
-        ha’hūnu	ހައިހޫނު
-        fa’isa	ފައިސަ
-        k’īn	ކްއީން
-      (c) When a consonant follows އް in medial position, double it in romanization.
-        cappalu	ޗައްޕަލު
-        appacci	އައްޕައްޗި
-      (d) When used in final position with ް (sukūn), romanize as h.
-        boh	ބޮއް
-        biheh	ބިހެއް
-    - |
-      Romanize ތް followed by another ތ as  t̤ .
-       at̤teri   އަތްތެރި
-    - |
-      Only the vowel forms that appear at the beginning of a syllable are listed.
-      When the vowels follow a consonant, އ is not used and the vowel signs are added to the consonant forms.
-      Do not distinguish between the two in romanization.
-    - |
-      ް (called sukūn) generally indicates omission of an inherent vowel associated with a consonant.
-      For its other uses, see Notes 1, 3, and 4.
-}
-
-tests {
-  test "މަށަށް", "maśaḫ"
-  test "އަނގަ", "aṁga"
-  test "ހަނދު", "haṁdu"
-  test "އަތަ", "ata"
-  test "އިދު", "idu"
-  test "އުމުރު", "umuru"
-  test "އެގަހުގި", "egahugi"
-  test "ފައިސަ", "faʼisa"
-  test "ބޮއް", "boh"
-  test "ބިހެއް", "biheh"
-  test "އަތްތެރި", "at̤teri"
-  test "ޗައްޕަލު", "cappalu"
-  test "އައްޕައްޗި", "appacci"
-}
-
-dependency "alalc-div-Thaa-Latn-1997", as: thaalatn
-
-stage {
-
-  run map.thaalatn.stage.main
-
-}