interscript-maps 2.2.0 → 2.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/interscript-maps.gemspec +1 -1
- data/interscript-maps.yaml +300 -111
- data/maps/acadsin-zho-Hani-Latn-2002.imp +2 -2
- data/maps/alalc-amh-Ethi-Latn-1997.imp +18 -14
- data/maps/alalc-amh-Ethi-Latn-2011.imp +1 -1
- data/maps/alalc-ara-Arab-Latn-1997.imp +1 -1
- data/maps/alalc-asm-Deva-Latn-1997.imp +1 -1
- data/maps/alalc-asm-Deva-Latn-2012.imp +1 -1
- data/maps/alalc-aze-Arab-Latn-1997.imp +1 -1
- data/maps/alalc-aze-Cyrl-Latn-1997.imp +1 -1
- data/maps/alalc-bel-Cyrl-Latn-1997.imp +4 -4
- data/maps/alalc-ben-Beng-Latn-1997.imp +1 -1
- data/maps/alalc-ben-Beng-Latn-2017.imp +1 -1
- data/maps/alalc-bul-Cyrl-Latn-1997.imp +1 -1
- data/maps/alalc-div-Thaa-Latn-1997.imp +1 -1
- data/maps/alalc-ell-Grek-Latn-1997.imp +1 -1
- data/maps/alalc-ell-Grek-Latn-2010.imp +1 -1
- data/maps/alalc-guj-Gujr-Latn-1997.imp +1 -1
- data/maps/alalc-guj-Gujr-Latn-2011.imp +1 -1
- data/maps/alalc-hin-Deva-Latn-1997.imp +1 -1
- data/maps/alalc-hin-Deva-Latn-2011.imp +1 -1
- data/maps/alalc-kan-Kana-Latn-1997.imp +1 -1
- data/maps/alalc-kan-Kana-Latn-2011.imp +1 -1
- data/maps/alalc-kat-Geok-Latn-1997.imp +3 -3
- data/maps/alalc-kat-Geor-Latn-1997.imp +12 -12
- data/maps/alalc-kor-Hang-Latn-1997.imp +1 -1
- data/maps/alalc-mal-Mlym-Latn-1997.imp +1 -1
- data/maps/alalc-mar-Deva-Latn-1997.imp +1 -1
- data/maps/alalc-mar-Deva-Latn-2011.imp +1 -1
- data/maps/alalc-mkd-Cyrl-Latn-1997.imp +2 -2
- data/maps/alalc-mkd-Cyrl-Latn-2013.imp +2 -2
- data/maps/alalc-mon-Cyrl-Latn-1997.imp +3 -3
- data/maps/alalc-ori-Orya-Latn-1997.imp +1 -1
- data/maps/alalc-ori-Orya-Latn-2011.imp +1 -1
- data/maps/alalc-pan-Guru-Latn-1997.imp +1 -1
- data/maps/alalc-pan-Guru-Latn-2011.imp +1 -1
- data/maps/alalc-per-Arab-Latn-1997.imp +1 -1
- data/maps/alalc-pli-Deva-Latn-2012.imp +1 -1
- data/maps/alalc-pra-Deva-Latn-2012.imp +1 -1
- data/maps/alalc-rus-Cyrl-Latn-1997.imp +2 -2
- data/maps/alalc-rus-Cyrl-Latn-2012.imp +1 -1
- data/maps/alalc-san-Deva-Latn-2012.imp +1 -1
- data/maps/alalc-sin-Sinh-Latn-1997.imp +1 -1
- data/maps/alalc-sin-Sinh-Latn-2011.imp +1 -1
- data/maps/alalc-srp-Cyrl-Latn-1997.imp +2 -2
- data/maps/alalc-srp-Cyrl-Latn-2013.imp +1 -1
- data/maps/alalc-tam-Taml-Latn-1997.imp +1 -1
- data/maps/alalc-tam-Taml-Latn-2011.imp +1 -1
- data/maps/alalc-tel-Telu-Latn-1997.imp +2 -2
- data/maps/alalc-tel-Telu-Latn-2011.imp +1 -1
- data/maps/alalc-tir-Ethi-Latn-1997.imp +429 -0
- data/maps/alalc-tir-Ethi-Latn-2011.imp +85 -0
- data/maps/alalc-ukr-Cyrl-Latn-1997.imp +1 -1
- data/maps/alalc-ukr-Cyrl-Latn-2011.imp +1 -1
- data/maps/apcbg-bul-Cyrl-Latn-1995.imp +7 -4
- data/maps/az-aze-Cyrl-Latn-1939.imp +1 -0
- data/maps/az-aze-Cyrl-Latn-1958.imp +1 -0
- data/maps/bgn-jpn-Hrkt-Latn-1962.imp +5 -5
- data/maps/bgn-kor-Hang-Latn-1943.imp +1 -1
- data/maps/bgn-kor-Kore-Latn-1943.imp +1 -1
- data/maps/bgnpcgn-amh-Ethi-Latn-1967.imp +11 -11
- data/maps/bgnpcgn-ara-Arab-Latn-1956.imp +1 -1
- data/maps/bgnpcgn-arm-Armn-Latn-1981.imp +2 -2
- data/maps/bgnpcgn-aze-Cyrl-Latn-1993.imp +2 -2
- data/maps/bgnpcgn-bul-Cyrl-Latn-1952.imp +10 -4
- data/maps/bgnpcgn-bul-Cyrl-Latn-2013.imp +1 -1
- data/maps/bgnpcgn-deu-Latn-Latn-2000.imp +1 -1
- data/maps/bgnpcgn-div-Thaa-Latn-1972.imp +4 -4
- data/maps/bgnpcgn-div-Thaa-Latn-1988.imp +1 -1
- data/maps/bgnpcgn-ell-Grek-Latn-1962.imp +1 -1
- data/maps/bgnpcgn-ell-Grek-Latn-1996.imp +1 -1
- data/maps/bgnpcgn-fao-Latn-Latn-1964.imp +4 -3
- data/maps/bgnpcgn-fao-Latn-Latn-1968.imp +1 -1
- data/maps/bgnpcgn-fas-Arab-Latn-1956.imp +1 -1
- data/maps/bgnpcgn-isl-Latn-Latn-1964.imp +2 -2
- data/maps/bgnpcgn-isl-Latn-Latn-1968.imp +1 -1
- data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.imp +1 -1
- data/maps/bgnpcgn-kat-Geor-Latn-1981.imp +8 -8
- data/maps/bgnpcgn-kat-Geor-Latn-2009.imp +2 -2
- data/maps/bgnpcgn-kaz-Cyrl-Latn-1979.imp +4 -4
- data/maps/bgnpcgn-kir-Cyrl-Latn-1979.imp +3 -3
- data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.imp +1 -1
- data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.imp +4 -4
- data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.imp +4 -3
- data/maps/bgnpcgn-kur-Arab-Latn-2007.imp +1 -1
- data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.imp +2 -2
- data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.imp +1 -1
- data/maps/bgnpcgn-mon-Cyrl-Latn-1964.imp +3 -3
- data/maps/bgnpcgn-nep-Deva-Latn-2011.imp +4 -4
- data/maps/bgnpcgn-per-Arab-Latn-1958.imp +19 -19
- data/maps/bgnpcgn-prs-Arab-Latn-2007.imp +15 -15
- data/maps/bgnpcgn-prs-Arab-Latn-yaghoubi.imp +15 -15
- data/maps/bgnpcgn-pus-Arab-Latn-1968.imp +16 -16
- data/maps/bgnpcgn-ron-cyrl-latn-2002.imp +2 -2
- data/maps/bgnpcgn-rue-Cyrl-Latn-2016.imp +5 -5
- data/maps/bgnpcgn-rus-Cyrl-Latn-1947.imp +1 -1
- data/maps/bgnpcgn-sme-Latn-Latn-1984.imp +1 -1
- data/maps/bgnpcgn-srp-Cyrl-Latn-1962.imp +5 -3
- data/maps/bgnpcgn-srp-Cyrl-Latn-2005.imp +1 -1
- data/maps/bgnpcgn-tat-Cyrl-Latn-2007.imp +1 -1
- data/maps/bgnpcgn-tgk-Cyrl-Latn-1994.imp +1 -1
- data/maps/bgnpcgn-tir-Ethi-Latn-2007.imp +511 -0
- data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.imp +1 -1
- data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.imp +1 -1
- data/maps/bgnpcgn-urd-Arab-Latn-2007.imp +15 -15
- data/maps/bgnpcgn-uzb-Cyrl-Latn-1979.imp +3 -3
- data/maps/bgnpcgn-uzb-Cyrl-Latn-2000.imp +1 -1
- data/maps/bgnpcgn-zho-Hans-Latn-1979.imp +1 -1
- data/maps/by-bel-Cyrl-Latn-2007.imp +7 -5
- data/maps/dos-nep-Deva-Latn-1997.imp +2 -2
- data/maps/elot-ell-Grek-Latn-743-1982-ts.imp +1 -1
- data/maps/elot-ell-Grek-Latn-743-2001-tl.imp +1 -1
- data/maps/ggg-kat-Geor-Latn-2002.imp +3 -3
- data/maps/gki-bel-Cyrl-Latn-2000.imp +1 -1
- data/maps/gost-rus-Cyrl-Latn-16876-71-1983.imp +1 -1
- data/maps/iso-ara-Arab-Latn-233-1984.imp +14 -14
- data/maps/iso-ben-Beng-Latn-15919-2001.imp +1 -1
- data/maps/iso-prs-Arab-Latn-233-3-1999.imp +14 -14
- data/maps/lshk-yue-Hani-Latn-jyutping-1993.imp +5 -5
- data/maps/mext-jpn-Hrkt-Latn-1954.imp +2 -1
- data/maps/moct-kor-Hang-Latn-2000.imp +1 -1
- data/maps/mofa-jpn-Hrkt-Latn-1989.imp +1 -1
- data/maps/mv-div-Thaa-Latn-1987.imp +1 -1
- data/maps/mvd-bel-Cyrl-Latn-2008.imp +5 -5
- data/maps/mvd-bel-Cyrl-Latn-2010.imp +2 -5
- data/maps/mvd-rus-Cyrl-Latn-2008.imp +4 -3
- data/maps/mvd-rus-Cyrl-Latn-2010.imp +2 -5
- data/maps/odni-ara-Arab-Latn-2004.imp +1 -1
- data/maps/odni-ara-Arab-Latn-2015.imp +1 -1
- data/maps/odni-aze-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-bel-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-bul-Cyrl-Latn-2005.imp +2 -2
- data/maps/odni-bul-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-che-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-fas-Arab-Latn-2004.imp +14 -14
- data/maps/odni-fas-Arab-Latn-2015.imp +15 -15
- data/maps/odni-hin-Deva-Latn-2004.imp +20 -20
- data/maps/odni-hin-Deva-Latn-2015.imp +25 -26
- data/maps/odni-kat-Geor-Latn-2015.imp +2 -3
- data/maps/odni-kaz-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-kir-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-kor-Hang-Latn-2015.imp +1 -1
- data/maps/odni-mkd-Cyrl-Latn-2005.imp +1 -1
- data/maps/odni-mkd-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-prs-Arab-Latn-2015.imp +1 -1
- data/maps/odni-pus-Arab-Latn-2011.imp +1 -1
- data/maps/odni-rus-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-srp-Cyrl-Latn-2005.imp +2 -2
- data/maps/odni-srp-Cyrl-Latn-2015.imp +8 -8
- data/maps/odni-tat-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-tgk-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-tuk-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-uig-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-ukr-Cyrl-Latn-2015.imp +1 -1
- data/maps/odni-urd-Arab-Latn-2015.imp +21 -21
- data/maps/odni-uzb-Cyrl-Latn-2015.imp +1 -1
- data/maps/ses-ara-Arab-Latn-1930.imp +14 -14
- data/maps/un-amh-Ethi-Latn-2016.imp +1 -1
- data/maps/un-ara-Arab-Latn-1971.imp +5 -5
- data/maps/un-ara-Arab-Latn-1972.imp +4 -4
- data/maps/un-ara-Arab-Latn-2017.imp +15 -15
- data/maps/un-asm-Beng-Latn-1972.imp +1 -1
- data/maps/un-bel-Cyrl-Latn-2007.imp +2 -2
- data/maps/un-ben-Beng-Latn-2016.imp +1 -1
- data/maps/un-bul-Cyrl-Latn-1977.imp +197 -0
- data/maps/un-ell-Grek-Latn-1987-phonetic.imp +5 -1
- data/maps/un-ell-Grek-Latn-1987-tl.imp +1 -1
- data/maps/un-ell-Grek-Latn-1987-ts.imp +2 -2
- data/maps/un-guj-Gujr-Latn-1972.imp +1 -1
- data/maps/un-hin-Deva-Latn-2016.imp +1 -1
- data/maps/un-kan-Kana-Latn-2016.imp +1 -1
- data/maps/un-mal-Mlym-Latn-1972.imp +1 -1
- data/maps/un-mar-Deva-Latn-2016.imp +1 -1
- data/maps/un-mkd-Cyrl-Latn-1977.imp +119 -0
- data/maps/un-mon-Mong-Latn-general-2013.imp +1 -1
- data/maps/un-mon-Mong-Latn-phonetic-2013.imp +1 -1
- data/maps/un-nep-Deva-Latn-1972.imp +1 -1
- data/maps/un-nep-Deva-Latn-2013.imp +1 -1
- data/maps/un-ori-Orya-Latn-1972.imp +1 -1
- data/maps/un-pan-Guru-Latn-1972.imp +1 -1
- data/maps/un-prs-Arab-Latn-1967.imp +15 -15
- data/maps/un-rus-Cyrl-Latn-1987.imp +1 -1
- data/maps/un-sin-Sinh-Latn-1972.imp +1 -1
- data/maps/un-srp-Cyrl-Latn-1997.imp +47 -0
- data/maps/un-tam-Taml-Latn-1972.imp +1 -1
- data/maps/un-tel-Telu-Latn-1972.imp +1 -1
- data/maps/un-ukr-Cyrl-Latn-1998.imp +1 -1
- data/maps/un-ukr-Cyrl-Latn-2012.imp +1 -1
- data/maps/un-urd-Arab-Latn-1972.imp +15 -15
- data/maps/var-amh-Ethi-Latn-eae-2003.imp +48 -43
- metadata +7 -1
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:ukr
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Romanization of Ukrainian (1965)
|
8
8
|
url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816788/ROMANIZATION_OF_UKRAINIAN.pdf
|
9
9
|
creation_date: 1947
|
10
10
|
confirmation_date: 2019-06
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:ukr
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Romanization of Ukrainian (2019 Agreement)
|
8
8
|
url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/864314/ROMANIZATION_OF_UKRAINIAN.pdf
|
9
9
|
creation_date: 2019
|
10
10
|
confirmation_date: 2020-01
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:urd
|
5
5
|
source_script: Arab
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Romanization of Urdu (2007)
|
8
8
|
url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693788/ROMANIZATION_OF_URDU.pdf
|
9
9
|
creation_date: 2007
|
10
10
|
confirmation_date: 2017-11
|
@@ -251,20 +251,20 @@ stage {
|
|
251
251
|
# '\uFE8E' : '' # ﺎ
|
252
252
|
|
253
253
|
# Sun letters
|
254
|
-
sub boundary + "\u0627\u0644\u062a", "at t" # الت
|
255
|
-
sub boundary + "\u0627\u0644\u062b", "as̄ s̄" # الث
|
256
|
-
sub boundary + "\u0627\u0644\u062f", "ad d" # الد
|
257
|
-
sub boundary + "\u0627\u0644\u0630", "az̄ z̄" # الذ
|
258
|
-
sub boundary + "\u0627\u0644\u0631", "ar r" # الر
|
259
|
-
sub boundary + "\u0627\u0644\u0632", "az z" # الز
|
260
|
-
sub boundary + "\u0627\u0644\u0633", "as s" # الس
|
261
|
-
sub boundary + "\u0627\u0644\u0634", "ash sh" # الش
|
262
|
-
sub boundary + "\u0627\u0644\u0635", "aş ş" # الص
|
263
|
-
sub boundary + "\u0627\u0644\u0636", "aẕ ẕ" # الض
|
264
|
-
sub boundary + "\u0627\u0644\u0637", "aţ ţ" # الط
|
265
|
-
sub boundary + "\u0627\u0644\u0638", "az̧ z̧" # الظ
|
266
|
-
sub boundary + "\u0627\u0644\u0644", "al l" # الل
|
267
|
-
sub boundary + "\u0627\u0644\u0646", "an n" # الن
|
254
|
+
sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "at t" # الت
|
255
|
+
sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "as̄ s̄" # الث
|
256
|
+
sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
|
257
|
+
sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "az̄ z̄" # الذ
|
258
|
+
sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "ar r" # الر
|
259
|
+
sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "az z" # الز
|
260
|
+
sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "as s" # الس
|
261
|
+
sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "ash sh" # الش
|
262
|
+
sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "aş ş" # الص
|
263
|
+
sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aẕ ẕ" # الض
|
264
|
+
sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aţ ţ" # الط
|
265
|
+
sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az̧ z̧" # الظ
|
266
|
+
sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
|
267
|
+
sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
|
268
268
|
|
269
269
|
|
270
270
|
# consonant characters
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:uzb
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Romanization of Uzbek Cyrillic (1979)
|
8
8
|
url: http://transliteration.eki.ee/pdf/Uzbek.pdf
|
9
9
|
creation_date: 1979
|
10
10
|
|
@@ -30,7 +30,7 @@ tests {
|
|
30
30
|
}
|
31
31
|
|
32
32
|
aliases {
|
33
|
-
|
33
|
+
|
34
34
|
def_alias uzbek_upper, any("\u0410\u0411\u0412\u0413\u0492\u0414\u0415\u0401\u0416\u0417\u0418\u0419\u041A\u049A\u041B\u041C\u041D\u041E\u041F\u0420\u0421\u0422\u0423\u040E\u0424\u04B2\u0426\u0427\u0428\u042a\u042c\u042D\u042E\u042F")
|
35
35
|
|
36
36
|
}
|
@@ -55,7 +55,7 @@ stage {
|
|
55
55
|
sub "\u0401", "Yo" # Ё
|
56
56
|
sub "\u0401", "YO", after: any("АБВГҒДЕЁЖЗИЙКҚЛМНОПРСТУЎФҲЦЧШЪЬЭЮЯ") # Ё
|
57
57
|
sub "\u0401", "YO", before: any("АБВГҒДЕЁЖЗИЙКҚЛМНОПРСТУЎФҲЦЧШЪЬЭЮЯ") # Ё
|
58
|
-
|
58
|
+
|
59
59
|
sub "\u0416", "Zh" # Ж
|
60
60
|
sub "\u0416", "ZH", after: any("АБВГҒДЕЁЖЗИЙКҚЛМНОПРСТУЎФҲЦЧШЪЬЭЮЯ") # Ж
|
61
61
|
sub "\u0416", "ZH", before: any("АБВГҒДЕЁЖЗИЙКҚЛМНОПРСТУЎФҲЦЧШЪЬЭЮЯ") # Ж
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:uzb
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Table of Correspondences for Uzbek (Cyrillic-Roman) (2000 Agreement)
|
8
8
|
description: |
|
9
9
|
In 1995, the Uzbek government adopted the Roman alphabet to replace the existing Cyrillic alphabet.
|
10
10
|
The presentation below provides a table of correspondences between the former Cyrillic alphabet and the
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:zho
|
5
5
|
source_script: Hans
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Romanization of Chinese (1979 Agreement)
|
8
8
|
url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693689/ROMANIZATION_OF_CHINESE.pdf
|
9
9
|
creation_date: 1979
|
10
10
|
confirmation_date: 2017-12
|
@@ -4,19 +4,21 @@ metadata {
|
|
4
4
|
language: iso-639-2:bel
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Transliteration of geographical names of the Republic of Belarus in letters of the Latin alphabet (2007)
|
8
8
|
url: http://www.pravo.by/pdf/2007-159/2007-159(027-028).pdf
|
9
9
|
creation_date: 2007
|
10
10
|
description: |
|
11
11
|
RESOLUTION OF THE STATE COMMITTEE
|
12
12
|
ON PROPERTY OF THE REPUBLIC OF BELARUS June 11, 2007 No. 38
|
13
13
|
|
14
|
-
|
15
|
-
|
16
|
-
|
14
|
+
Regulatory Legal Acts Of The National Bank, National Academy Of Sciences Of
|
15
|
+
Belarus, Ministries, Other Republican Government Bodies 8/16668 (06/18/2007)
|
16
|
+
On amendments and additions to the Instructions for the transliteration of
|
17
|
+
geographical names of the Republic of Belarus in letters of the Latin
|
18
|
+
alphabet
|
17
19
|
|
18
20
|
Based on the Regulation on the State Property Committee of the Republic of Belarus,
|
19
|
-
approved by the Decree of the Council of Ministers of the Republic of
|
21
|
+
approved by the Decree of the Council of Ministers of the Republic of Belarus dated July 29, 2006
|
20
22
|
No. 958 "Issues of the State Committee on Property of the Republic of Belarus"
|
21
23
|
}
|
22
24
|
|
@@ -1,10 +1,10 @@
|
|
1
1
|
metadata {
|
2
|
-
authority_id:
|
2
|
+
authority_id: dos
|
3
3
|
id: 1997
|
4
4
|
language: iso-639-2:nep
|
5
5
|
source_script: Deva
|
6
6
|
destination_script: Latn
|
7
|
-
name: Nepali Romanization
|
7
|
+
name: Survey Department Nepali Romanization System (1997)
|
8
8
|
url: http://nationalgeoportal.gov.np/old/pdf/translation2.pdf
|
9
9
|
creation_date: 1997
|
10
10
|
description: |
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:kat
|
5
5
|
source_script: Geor
|
6
6
|
destination_script: Latn
|
7
|
-
name: Georgian State Department of Geodesy and Cartography
|
7
|
+
name: Georgian State Department of Geodesy and Cartography Romanization System (2002)
|
8
8
|
url: https://transliteration.eki.ee/pdf/Georgian.pdf
|
9
9
|
creation_date: 1998
|
10
10
|
confirmation_date: 2002
|
@@ -12,10 +12,10 @@ metadata {
|
|
12
12
|
The national system of romanization adopted in February 2002 by the State
|
13
13
|
Department of Geodesy and Cartography of Georgia and the Institute
|
14
14
|
of Linguistics, Georgian Academy of Sciences.
|
15
|
-
|
15
|
+
|
16
16
|
notes:
|
17
17
|
- Georgian script refers in this document to the Mkhedruli alphabet.
|
18
|
-
|
18
|
+
|
19
19
|
- There is no case in Georgian.
|
20
20
|
}
|
21
21
|
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:bel
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Transliteration of geographical names of the Republic of Belarus with letters of the Latin alphabet (2000)
|
8
8
|
url: https://registr.by/doc/103003
|
9
9
|
creation_date: 2000
|
10
10
|
description: |
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:rus
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: GOST 16876-71 Translation Rules Of Cyrillic Alphabet Letters With Latin Alphabet Letters (Table 1)
|
8
8
|
url: http://vsegost.com/Catalog/45/45002.shtml
|
9
9
|
creation_date: 1978
|
10
10
|
confirmation_date: 1982-04-16
|
@@ -84,20 +84,20 @@ stage {
|
|
84
84
|
|
85
85
|
# Sun letters
|
86
86
|
|
87
|
-
sub boundary + "\u0627\u0644\u062a", "at t" # الت
|
88
|
-
sub boundary + "\u0627\u0644\u062b", "aṯ ṯ" # الث
|
89
|
-
sub boundary + "\u0627\u0644\u062f", "ad d" # الد
|
90
|
-
sub boundary + "\u0627\u0644\u0630", "aḏ ḏ" # الذ
|
91
|
-
sub boundary + "\u0627\u0644\u0631", "ar r" # الر
|
92
|
-
sub boundary + "\u0627\u0644\u0632", "az z" # الز
|
93
|
-
sub boundary + "\u0627\u0644\u0633", "as s" # الس
|
94
|
-
sub boundary + "\u0627\u0644\u0634", "aš š" # الش
|
95
|
-
sub boundary + "\u0627\u0644\u0635", "aṣ ṣ" # الص
|
96
|
-
sub boundary + "\u0627\u0644\u0636", "aḍ ḍ" # الض
|
97
|
-
sub boundary + "\u0627\u0644\u0637", "aṭ ṭ" # الط
|
98
|
-
sub boundary + "\u0627\u0644\u0638", "aẓ ẓ" # الظ
|
99
|
-
sub boundary + "\u0627\u0644\u0644", "al l" # الل
|
100
|
-
sub boundary + "\u0627\u0644\u0646", "an n" # الن
|
87
|
+
sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "at t" # الت
|
88
|
+
sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "aṯ ṯ" # الث
|
89
|
+
sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
|
90
|
+
sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "aḏ ḏ" # الذ
|
91
|
+
sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "ar r" # الر
|
92
|
+
sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "az z" # الز
|
93
|
+
sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "as s" # الس
|
94
|
+
sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "aš š" # الش
|
95
|
+
sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "aṣ ṣ" # الص
|
96
|
+
sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aḍ ḍ" # الض
|
97
|
+
sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aṭ ṭ" # الط
|
98
|
+
sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "aẓ ẓ" # الظ
|
99
|
+
sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
|
100
|
+
sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
|
101
101
|
|
102
102
|
# ta' marboota in iso-233-1984 is all the same `aẗ`
|
103
103
|
sub "\u0629", "aẗ" # ة in the middle of the sentence
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:ben
|
5
5
|
source_script: Beng
|
6
6
|
destination_script: Latn
|
7
|
-
name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
|
7
|
+
name: "ISO 15919:2001 - Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
|
8
8
|
url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
|
9
9
|
creation_date: 2001
|
10
10
|
adoption_date: 2001
|
@@ -245,20 +245,20 @@ stage {
|
|
245
245
|
# '\uFE8E' : '' # ﺎ
|
246
246
|
|
247
247
|
# Sun letters
|
248
|
-
sub boundary + "\u0627\u0644\u062a", "at t" # الت
|
249
|
-
sub boundary + "\u0627\u0644\u062b", "as̄ s̄" # الث
|
250
|
-
sub boundary + "\u0627\u0644\u062f", "ad d" # الد
|
251
|
-
sub boundary + "\u0627\u0644\u0630", "az̄ z̄" # الذ
|
252
|
-
sub boundary + "\u0627\u0644\u0631", "ar r" # الر
|
253
|
-
sub boundary + "\u0627\u0644\u0632", "az z" # الز
|
254
|
-
sub boundary + "\u0627\u0644\u0633", "as s" # الس
|
255
|
-
sub boundary + "\u0627\u0644\u0634", "ash sh" # الش
|
256
|
-
sub boundary + "\u0627\u0644\u0635", "aş ş" # الص
|
257
|
-
sub boundary + "\u0627\u0644\u0636", "aẕ ẕ" # الض
|
258
|
-
sub boundary + "\u0627\u0644\u0637", "aţ ţ" # الط
|
259
|
-
sub boundary + "\u0627\u0644\u0638", "az̧ z̧" # الظ
|
260
|
-
sub boundary + "\u0627\u0644\u0644", "al l" # الل
|
261
|
-
sub boundary + "\u0627\u0644\u0646", "an n" # الن
|
248
|
+
sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "at t" # الت
|
249
|
+
sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "as̄ s̄" # الث
|
250
|
+
sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
|
251
|
+
sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "az̄ z̄" # الذ
|
252
|
+
sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "ar r" # الر
|
253
|
+
sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "az z" # الز
|
254
|
+
sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "as s" # الس
|
255
|
+
sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "ash sh" # الش
|
256
|
+
sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "aş ş" # الص
|
257
|
+
sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aẕ ẕ" # الض
|
258
|
+
sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aţ ţ" # الط
|
259
|
+
sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az̧ z̧" # الظ
|
260
|
+
sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
|
261
|
+
sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
|
262
262
|
|
263
263
|
# consonant characters
|
264
264
|
|
@@ -4,11 +4,11 @@ metadata {
|
|
4
4
|
language: iso-639-3:yue
|
5
5
|
source_script: Hani
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Jyutping Cantonese Romanisation Scheme
|
8
8
|
url: https://lshk.org/jyutping
|
9
9
|
creation_date: 1993-12
|
10
10
|
description:
|
11
|
-
- The Linguistic Society of Hong Kong Cantonese
|
11
|
+
- The Linguistic Society of Hong Kong Cantonese Romanisation Scheme, or
|
12
12
|
known as Jyutping, was designed and proposed by the Linguistic Society of
|
13
13
|
Hong Kong in 1993. Jyutping is a new Cantonese romanization system which
|
14
14
|
has many advantages. It is multifunctional, systematic, user-friendly,
|
@@ -16,12 +16,12 @@ metadata {
|
|
16
16
|
alphanumeric characters without any diacritics and strange symbols.
|
17
17
|
Jyutping can also be used as a Chinese computer input method. Its basic
|
18
18
|
principles are simple, easy to learn, and professional.
|
19
|
-
|
19
|
+
|
20
20
|
notes:
|
21
21
|
- One may need to parse the text in order to generate accurate
|
22
22
|
transliteration.
|
23
|
-
|
24
|
-
|
23
|
+
|
24
|
+
|
25
25
|
#A longer test list will be generated from GeoNames database
|
26
26
|
}
|
27
27
|
|
@@ -4,7 +4,8 @@ metadata {
|
|
4
4
|
language: iso-639-2:jpn
|
5
5
|
source_script: Hrkt
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Japanese Cabinet Romanisation of Japanese
|
8
|
+
# name: 内閣告示第一号 -- ローマ字のつづり方
|
8
9
|
url: http://www.mext.go.jp/b_menu/hakusho/nc/k19541209001/k19541209001.html
|
9
10
|
creation_date: 1954
|
10
11
|
adoption_date: 1954-12-09
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:kor
|
5
5
|
source_script: Hang
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Ministry of Culture and Tourism Korean Romanization System (2000)
|
8
8
|
url: https://www.korean.go.kr/front_eng/roman/roman_01.do
|
9
9
|
creation_date: 2000
|
10
10
|
adoption_date: 2002
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:jpn
|
5
5
|
source_script: Hrkt
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
7
|
+
name: Ministry of Foreign Affairs of Japan Hepburn Romanization
|
8
8
|
url: https://www.ezairyu.mofa.go.jp/passport/hebon.html
|
9
9
|
creation_date:
|
10
10
|
adoption_date:
|
@@ -4,7 +4,7 @@ metadata {
|
|
4
4
|
language: iso-639-2:div
|
5
5
|
source_script: Thaa
|
6
6
|
destination_script: Latn
|
7
|
-
name: Maldivian (Divehi)
|
7
|
+
name: Maldivian (Divehi) Romanization system (1987)
|
8
8
|
url: https://www.eki.ee/wgrs/rom2_dv.htm
|
9
9
|
creation_date: 1887
|
10
10
|
description: |
|
@@ -4,8 +4,8 @@ metadata {
|
|
4
4
|
language: iso-639-2:bel
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
8
|
-
url:
|
7
|
+
name: Transliteration system for Belarusian names in the population register (2008)
|
8
|
+
url:
|
9
9
|
creation_date: 2008
|
10
10
|
|
11
11
|
description: |
|
@@ -127,9 +127,9 @@ stage {
|
|
127
127
|
sub "\u0412", "V" # B
|
128
128
|
sub "\u0413", "G" # Г
|
129
129
|
sub "\u0414", "D" # Д
|
130
|
-
sub "\u0415", "Ie" # Е or JE TODO add rule
|
131
|
-
sub "\u0415", "IE", after: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Е or JE TODO add rule
|
132
|
-
sub "\u0415", "IE", before: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Е or JE TODO add rule
|
130
|
+
sub "\u0415", "Ie" # Е or JE TODO add rule
|
131
|
+
sub "\u0415", "IE", after: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Е or JE TODO add rule
|
132
|
+
sub "\u0415", "IE", before: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Е or JE TODO add rule
|
133
133
|
sub "\u0401", "Io" # Ё or JO TODO add rule
|
134
134
|
sub "\u0401", "IO", after: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Ё or JO TODO add rule
|
135
135
|
sub "\u0401", "IO", before: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Ё or JO TODO add rule
|
@@ -4,17 +4,14 @@ metadata {
|
|
4
4
|
language: iso-639-2:bel
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
8
|
-
8/22721 About approval of the Instructions on the organization of work of units of citizenship
|
9
|
-
and migration of internal affairs bodies on the issuance, registration, exchange,
|
10
|
-
invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
|
7
|
+
name: Transliteration system for Belarusian names (2010)
|
11
8
|
url: https://pravo.by/document/?guid=3871&p0=W21022721
|
12
9
|
creation_date: 2010
|
13
10
|
|
14
11
|
description: |
|
15
12
|
RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
|
16
13
|
June 28, 2010 No. 200
|
17
|
-
|
14
|
+
8/22721 About approval of the Instructions on the organization of work of units of citizenship
|
18
15
|
and migration of internal affairs bodies on the issuance, registration, exchange,
|
19
16
|
invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
|
20
17
|
|
@@ -4,10 +4,11 @@ metadata {
|
|
4
4
|
language: iso-639-2:rus
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
8
|
-
url:
|
7
|
+
name: Transliteration system for Russian names in the population register (2008)
|
8
|
+
url:
|
9
9
|
creation_date: 2008
|
10
|
-
|
10
|
+
description: |
|
11
|
+
8/19678 On approval of the Instructions for transliteration of surnames and proper names of citizens of the Republic of Belarus when their personal data is included in the population register
|
11
12
|
notes:
|
12
13
|
- check notes from mvd-bel-Cyrl-Latn-2008
|
13
14
|
}
|
@@ -4,17 +4,14 @@ metadata {
|
|
4
4
|
language: iso-639-2:bel
|
5
5
|
source_script: Cyrl
|
6
6
|
destination_script: Latn
|
7
|
-
name:
|
8
|
-
8/22721 On approval of the Instructions on the organization of work of units of citizenship
|
9
|
-
and migration of internal affairs bodies on the issuance, registration, exchange,
|
10
|
-
invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
|
7
|
+
name: Transliteration system for Russian names (2010)
|
11
8
|
url: https://pravo.by/document/?guid=3871&p0=W21022721
|
12
9
|
creation_date: 2010
|
13
10
|
|
14
11
|
description: |
|
15
12
|
RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
|
16
13
|
June 28, 2010 No. 200
|
17
|
-
On approval of the Instructions on the organization of work of units of citizenship
|
14
|
+
8/22721 On approval of the Instructions on the organization of work of units of citizenship
|
18
15
|
and migration of internal affairs bodies on the issuance, registration, exchange,
|
19
16
|
invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
|
20
17
|
|