interscript 0.1.2 → 0.1.7
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.adoc +250 -17
- data/lib/g2pwrapper.py +34 -0
- data/lib/interscript.rb +142 -20
- data/lib/interscript/command.rb +28 -0
- data/lib/interscript/fs.rb +69 -0
- data/lib/interscript/mapping.rb +142 -0
- data/lib/interscript/opal.rb +57 -0
- data/lib/interscript/opal/entrypoint.rb +12 -0
- data/lib/interscript/opal/map_translate.rb +7 -0
- data/lib/interscript/opal/maps.js.erb +10 -0
- data/lib/interscript/version.rb +1 -1
- data/lib/model-7 +0 -0
- data/lib/tha-pt-b-7 +0 -0
- data/maps/acadsin-zho-Hani-Latn-2002.yaml +38916 -0
- data/maps/alalc-amh-Ethi-Latn-1997.yaml +513 -0
- data/maps/alalc-amh-Ethi-Latn-2011.yaml +138 -0
- data/maps/alalc-ara-Arab-Latn-1997.yaml +1287 -0
- data/maps/alalc-asm-Deva-Latn-1997.yaml +165 -0
- data/maps/alalc-asm-Deva-Latn-2012.yaml +40 -0
- data/maps/alalc-aze-Cyrl-Latn-1997.yaml +145 -0
- data/maps/alalc-bel-Cyrl-Latn-1997.yaml +129 -0
- data/maps/alalc-ben-Beng-Latn-2017.yaml +130 -0
- data/maps/alalc-bul-Cyrl-Latn-1997.yaml +98 -0
- data/maps/alalc-ell-Grek-Latn-1997.yaml +628 -0
- data/maps/alalc-ell-Grek-Latn-2010.yaml +626 -0
- data/maps/alalc-guj-Gujr-Latn-1997.yaml +266 -0
- data/maps/alalc-guj-Gujr-Latn-2011.yaml +64 -0
- data/maps/alalc-hin-Deva-Latn-1997.yaml +211 -0
- data/maps/alalc-hin-Deva-Latn-2011.yaml +47 -0
- data/maps/alalc-kat-Geok-Latn-1997.yaml +111 -0
- data/maps/alalc-kat-Geor-Latn-1997.yaml +150 -0
- data/maps/alalc-kor-Hang-Latn-1997.yaml +98 -0
- data/maps/alalc-mal-Mlym-Latn-1997.yaml +303 -0
- data/maps/alalc-mal-Mlym-Latn-2012.yaml +73 -0
- data/maps/alalc-mar-Deva-Latn-1997.yaml +189 -0
- data/maps/alalc-mar-Deva-Latn-2011.yaml +45 -0
- data/maps/alalc-mkd-Cyrl-Latn-1997.yaml +114 -0
- data/maps/alalc-mkd-Cyrl-Latn-2013.yaml +103 -0
- data/maps/alalc-mon-Cyrl-Latn-1997.yaml +220 -0
- data/maps/alalc-pan-Guru-Latn-1997.yaml +256 -0
- data/maps/alalc-pan-Guru-Latn-2011.yaml +78 -0
- data/maps/alalc-per-Arab-Latn-1997.yaml +375 -0
- data/maps/alalc-pli-Deva-Latn-2012.yaml +144 -0
- data/maps/alalc-pra-Deva-Latn-2012.yaml +47 -0
- data/maps/alalc-rus-Cyrl-Latn-1997.yaml +225 -0
- data/maps/alalc-rus-Cyrl-Latn-2012.yaml +162 -0
- data/maps/alalc-san-Deva-Latn-2012.yaml +172 -0
- data/maps/alalc-sin-Sinh-Latn-1997.yaml +292 -0
- data/maps/alalc-sin-Sinh-Latn-2011.yaml +71 -0
- data/maps/alalc-srp-Cyrl-Latn-1997.yaml +118 -0
- data/maps/alalc-srp-Cyrl-Latn-2013.yaml +135 -0
- data/maps/alalc-tam-Taml-Latn-1997.yaml +62 -0
- data/maps/alalc-tam-Taml-Latn-2011.yaml +58 -0
- data/maps/alalc-ukr-Cyrl-Latn-1997.yaml +145 -0
- data/maps/alalc-ukr-Cyrl-Latn-2011.yaml +16 -0
- data/maps/apcbg-bul-Cyrl-Latn-1995.yaml +283 -0
- data/maps/{bas-rus-Cyrl-Latn-bss.yaml → bas-rus-Cyrl-Latn-2017-bss.yaml} +58 -33
- data/maps/{bas-rus-Cyrl-Latn-oss.yaml → bas-rus-Cyrl-Latn-2017-oss.yaml} +55 -35
- data/maps/bgn-jpn-Hrkt-Latn-1962.yaml +292 -0
- data/maps/bgn-kor-Hang-Latn-1943.yaml +35 -0
- data/maps/bgn-kor-Kore-Latn-1943.yaml +31 -0
- data/maps/bgna-bul-Cyrl-Latn-2006.yaml +208 -0
- data/maps/bgna-bul-Cyrl-Latn-2009.yaml +208 -0
- data/maps/bgnpcgn-amh-Ethi-Latn-1967.yaml +532 -0
- data/maps/bgnpcgn-ara-Arab-Latn-1956.yaml +596 -0
- data/maps/bgnpcgn-arm-Armn-Latn-1981.yaml +2 -3
- data/maps/bgnpcgn-aze-Cyrl-Latn-1993.yaml +104 -0
- data/maps/bgnpcgn-bak-Cyrl-Latn-2007.yaml +188 -0
- data/maps/bgnpcgn-bel-Cyrl-Latn-1979.yaml +289 -0
- data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml +119 -0
- data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml +15 -65
- data/maps/bgnpcgn-che-Cyrl-Latn-2008.yaml +184 -0
- data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml +705 -0
- data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml +23 -0
- data/maps/{bgnpcgn-per-Arab-Latn-1956.yaml → bgnpcgn-fas-Arab-Latn-1956.yaml} +5 -2
- data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.yaml +257 -0
- data/maps/bgnpcgn-kat-Geor-Latn-1981.yaml +131 -0
- data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml +42 -0
- data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml +253 -0
- data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml +48 -0
- data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml +48 -0
- data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml +163 -0
- data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml +190 -0
- data/maps/bgnpcgn-mon-Cyrl-Latn-1964.yaml +223 -0
- data/maps/bgnpcgn-nep-Deva-Latn-2011.yaml +230 -0
- data/maps/bgnpcgn-per-Arab-Latn-1958.yaml +336 -0
- data/maps/bgnpcgn-prs-Arab-Latn-2007.yaml +639 -0
- data/maps/bgnpcgn-prs-Arab-Latn-yaghoubi.yaml +459 -0
- data/maps/bgnpcgn-rue-Cyrl-Latn-2016.yaml +168 -0
- data/maps/bgnpcgn-rus-Cyrl-Latn-1947.yaml +150 -65
- data/maps/bgnpcgn-srp-Cyrl-Latn-2005.yaml +170 -0
- data/maps/bgnpcgn-tat-Cyrl-Latn-2007.yaml +220 -0
- data/maps/bgnpcgn-tgk-Cyrl-Latn-1994.yaml +240 -0
- data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.yaml +80 -4
- data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.yaml +119 -0
- data/maps/bgnpcgn-uzb-Cyrl-Latn-1979.yaml +127 -0
- data/maps/bgnpcgn-uzb-Cyrl-Latn-2000.yaml +82 -0
- data/maps/bgnpcgn-zho-Hans-Latn-1979.yaml +7456 -0
- data/maps/bis-asm-Beng-Latn-13194-1991.yaml +159 -0
- data/maps/bis-ben-Beng-Latn-13194-1991.yaml +156 -0
- data/maps/bis-dev-Deva-Latn-13194-1991.yaml +184 -0
- data/maps/bis-guj-Gujr-Latn-13194-1991.yaml +181 -0
- data/maps/bis-knd-Knda-Latn-13194-1991.yaml +173 -0
- data/maps/bis-mlm-Mlym-Latn-13194-1991.yaml +176 -0
- data/maps/bis-ori-Orya-Latn-13194-1991.yaml +160 -0
- data/maps/bis-pnj-Guru-Latn-13194-1991.yaml +175 -0
- data/maps/bis-tel-Telu-Latn-13194-1991.yaml +170 -0
- data/maps/bis-tml-Taml-Latn-13194-1991.yaml +155 -0
- data/maps/by-bel-Cyrl-Latn-1998.yaml +172 -0
- data/maps/by-bel-Cyrl-Latn-2007.yaml +115 -0
- data/maps/din-grc-Grek-Latn-31634-2011-t1.yaml +899 -0
- data/maps/din-hin-Deva-Latn-33904-2018.yaml +100 -0
- data/maps/din-kat-Geor-Latn-32707-2010.yaml +145 -0
- data/maps/din-mar-Deva-Latn-33904-2018.yaml +84 -0
- data/maps/din-nep-Deva-Latn-33904-2018.yaml +119 -0
- data/maps/din-pli-Deva-Latn-33904-2018.yaml +75 -0
- data/maps/din-pra-Deva-Latn-33904-2018.yaml +63 -0
- data/maps/din-san-Deva-Latn-33904-2018.yaml +338 -0
- data/maps/din-tam-Taml-Latn-33903-2016.yaml +213 -0
- data/maps/dos-nep-Deva-Latn-1997.yaml +47 -0
- data/maps/elot-ell-Grek-Latn-743-1982-tl.yaml +684 -0
- data/maps/elot-ell-Grek-Latn-743-1982-ts.yaml +680 -0
- data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml +19 -0
- data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml +31 -0
- data/maps/ggg-kat-Geor-Latn-2002.yaml +92 -0
- data/maps/gki-bel-Cyrl-Latn-1992.yaml +33 -0
- data/maps/gki-bel-Cyrl-Latn-2000.yaml +201 -0
- data/maps/gost-rus-Cyrl-Latn-16876-71-1983.yaml +190 -0
- data/maps/gost-rus-Cyrl-Latn-7.79-2000-2002.yaml +157 -0
- data/maps/hk-yue-Hani-Latn-1888.yaml +38497 -0
- data/maps/icao-bel-Cyrl-Latn-9303.yaml +109 -98
- data/maps/icao-bul-Cyrl-Latn-9303.yaml +2 -7
- data/maps/{icao-per-Arab-Latn-9303.yaml → icao-fas-Arab-Latn-9303.yaml} +6 -8
- data/maps/icao-heb-Hebr-Latn-9303.yaml +119 -125
- data/maps/icao-mkd-Cyrl-Latn-9303.yaml +2 -3
- data/maps/icao-rus-Cyrl-Latn-9303.yaml +2 -4
- data/maps/icao-srp-Cyrl-Latn-9303.yaml +2 -3
- data/maps/icao-ukr-Cyrl-Latn-9303.yaml +2 -4
- data/maps/iso-ara-Arab-Latn-233-1984.yaml +323 -0
- data/maps/iso-asm-Beng-Latn-15919-2001.yaml +75 -0
- data/maps/iso-ben-Beng-Latn-15919-2001.yaml +175 -0
- data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml +613 -0
- data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml +44 -0
- data/maps/iso-guj-Gujr-Latn-15919-2001.yaml +220 -0
- data/maps/iso-hin-Deva-Latn-15919-2001.yaml +87 -0
- data/maps/iso-inc-Deva-Latn-15919-2001.yaml +61 -0
- data/maps/iso-jpn-Hrkt-Latn-3602-1989.yaml +66 -0
- data/maps/iso-kan-Knda-Latn-15919-2001.yaml +220 -0
- data/maps/iso-kat-Geor-Latn-9984-1996.yaml +145 -0
- data/maps/iso-kor-Hang-Latn-1996-method1.yaml +240 -0
- data/maps/iso-kor-Hang-Latn-1996-method2.yaml +226 -0
- data/maps/iso-mal-Mlym-Latn-15919-2001.yaml +281 -0
- data/maps/iso-mar-Deva-Latn-15919-2001.yaml +75 -0
- data/maps/iso-nep-Deva-Latn-15919-2001.yaml +87 -0
- data/maps/iso-ori-Orya-Latn-15919-2001.yaml +193 -0
- data/maps/iso-pan-Guru-Latn-15919-2001.yaml +222 -0
- data/maps/iso-pli-Beng-Latn-15919-2001.yaml +73 -0
- data/maps/iso-pli-Deva-Latn-15919-2001.yaml +74 -0
- data/maps/iso-pli-Sinh-Latn-15919-2001.yaml +219 -0
- data/maps/iso-pli-Thai-Latn-15919-2001.yaml +55 -0
- data/maps/iso-pra-Deva-Latn-15919-2001.yaml +59 -0
- data/maps/iso-prs-Arab-Latn-233-3-1999.yaml +366 -0
- data/maps/{iso-rus-Cyrl-Latn-iso9.yaml → iso-rus-Cyrl-Latn-9-1995.yaml} +4 -6
- data/maps/iso-san-Deva-Latn-15919-2001.yaml +220 -0
- data/maps/iso-tam-Taml-Latn-15919-2001.yaml +159 -0
- data/maps/iso-tel-Telu-Latn-15919-2001.yaml +220 -0
- data/maps/iso-tha-Thai-Latn-11940-1998.yaml +109 -0
- data/maps/kp-kor-Hang-Latn-2002.yaml +909 -0
- data/maps/lshk-yue-Hani-Latn-jyutping-1993.yaml +44820 -0
- data/maps/mext-jpn-Hrkt-Latn-1954.yaml +411 -0
- data/maps/mns-mon-Cyrl-Latn-5217-2012.yaml +163 -0
- data/maps/mns-mon-Latn-Cyrl-5217-2012.yaml +200 -0
- data/maps/moct-kor-Hang-Latn-2000.yaml +807 -0
- data/maps/mofa-jpn-Hrkt-Latn-1989.yaml +541 -0
- data/maps/mvd-bel-Cyrl-Latn-2008.yaml +225 -0
- data/maps/mvd-bel-Cyrl-Latn-2010.yaml +63 -0
- data/maps/mvd-rus-Cyrl-Latn-2008.yaml +109 -0
- data/maps/mvd-rus-Cyrl-Latn-2010.yaml +37 -0
- data/maps/odni-ara-Arab-Latn-2015.yaml +425 -0
- data/maps/odni-aze-Cyrl-Latn-2015.yaml +144 -0
- data/maps/odni-bel-Cyrl-Latn-2015.yaml +148 -0
- data/maps/odni-bul-Cyrl-Latn-2015.yaml +96 -0
- data/maps/odni-che-Cyrl-Latn-2015.yaml +169 -0
- data/maps/odni-fas-Arab-Latn-2015.yaml +406 -0
- data/maps/odni-hin-Deva-Latn-2015.yaml +258 -0
- data/maps/odni-kat-Geor-Latn-2015.yaml +87 -0
- data/maps/odni-kaz-Cyrl-Latn-2015.yaml +148 -0
- data/maps/odni-kir-Cyrl-Latn-2015.yaml +136 -0
- data/maps/odni-kor-Hang-Latn-2015.yaml +375 -0
- data/maps/odni-mkd-Cyrl-Latn-2015.yaml +122 -0
- data/maps/odni-per-Arab-Latn-2015.yaml +228 -0
- data/maps/odni-rus-Cyrl-Latn-2015.yaml +77 -0
- data/maps/odni-srp-Cyrl-Latn-2015.yaml +129 -0
- data/maps/odni-tat-Cyrl-Latn-2015.yaml +142 -0
- data/maps/odni-tgk-Cyrl-Latn-2015.yaml +148 -0
- data/maps/odni-uig-Cyrl-Latn-2015.yaml +138 -0
- data/maps/odni-ukr-Cyrl-Latn-2015.yaml +157 -0
- data/maps/odni-urd-Arab-Latn-2015.yaml +221 -0
- data/maps/odni-uzb-Cyrl-Latn-2015.yaml +166 -0
- data/maps/royin-tha-Thai-Latn-1939-generic.yaml +90 -0
- data/maps/royin-tha-Thai-Latn-1968.yaml +183 -0
- data/maps/royin-tha-Thai-Latn-1999-chained.yaml +180 -0
- data/maps/royin-tha-Thai-Latn-1999.yaml +80 -0
- data/maps/{cn-chn-Hans-Latn-pinyin.yaml → sac-zho-Hans-Latn-1979.yaml} +11 -8
- data/maps/sasm-mon-Mong-Latn-general-1978.yaml +389 -0
- data/maps/sasm-mon-Mong-Latn-phonetic-1978.yaml +354 -0
- data/maps/ses-ara-Arab-Latn-1930.yaml +283 -0
- data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml +222 -0
- data/maps/ua-ukr-Cyrl-Latn-1996.yaml +197 -0
- data/maps/ua-ukr-Cyrl-Latn-2007.yaml +75 -0
- data/maps/ua-ukr-Cyrl-Latn-2010.yaml +192 -0
- data/maps/un-amh-Ethi-Latn-2016.yaml +602 -0
- data/maps/un-ara-Arab-Latn-1971.yaml +139 -0
- data/maps/un-ara-Arab-Latn-1972.yaml +159 -0
- data/maps/un-ara-Arab-Latn-2017.yaml +420 -0
- data/maps/un-bel-Cyrl-Latn-2007.yaml +114 -0
- data/maps/un-ben-Beng-Latn-2016.yaml +534 -0
- data/maps/un-ell-Grek-Latn-1987-phonetic.yaml +780 -0
- data/maps/un-ell-Grek-Latn-1987-tl.yaml +31 -0
- data/maps/un-ell-Grek-Latn-1987-ts.yaml +19 -0
- data/maps/un-hin-Deva-Latn-2016.yaml +222 -0
- data/maps/un-mar-Deva-Latn-2016.yaml +91 -0
- data/maps/un-mon-Mong-Latn-general-2013.yaml +264 -0
- data/maps/un-mon-Mong-Latn-phonetic-2013.yaml +264 -0
- data/maps/un-nep-Deva-Latn-1972.yaml +350 -0
- data/maps/un-nep-Deva-Latn-2013.yaml +74 -0
- data/maps/un-rus-Cyrl-Latn-1987.yaml +166 -0
- data/maps/un-ukr-Cyrl-Latn-1998.yaml +53 -0
- data/maps/un-ukr-Cyrl-Latn-2012.yaml +162 -0
- data/maps/var-hin-Deva-Latn-hunterian-1872.yaml +221 -0
- data/maps/var-jpn-Hrkt-Latn-hepburn-1886.yaml +406 -0
- data/maps/var-jpn-Hrkt-Latn-hepburn-1954.yaml +386 -0
- data/maps/var-kor-Hang-Hang-jamo.yaml +11193 -0
- data/maps/var-kor-Hang-Latn-mr-1939.yaml +1054 -0
- data/maps/var-kor-Kore-Hang-2013.yaml +59754 -0
- data/maps/var-kor-Kore-Latn-mr-1939.yaml +36 -0
- data/maps/var-mar-Deva-Latn-hunterian-1872.yaml +43 -0
- data/maps/var-mon-Mong-Latn-1930.yaml +102 -0
- data/maps/var-mon-Mong-Latn-lessing.yaml +272 -0
- data/maps/var-mon-Mong-Latn-vpmc.yaml +274 -0
- data/maps/var-pra-Deva-Latn-iast-1912.yaml +30 -0
- data/maps/var-san-Deva-Latn-iast-1912.yaml +149 -0
- data/maps/var-tha-Thai-Thai-phonemic.yaml +59 -0
- data/maps/var-tha-Thai-Zsym-ipa.yaml +301 -0
- data/maps/var-zho-Hani-Latn-wd-1979.yaml +38912 -0
- data/spec/interscript/filenames_spec.rb +384 -0
- data/spec/interscript/mapping_spec.rb +42 -0
- data/spec/interscript_spec.rb +23 -5
- data/spec/spec_helper.rb +3 -1
- metadata +364 -34
- data/bin/interscript +0 -20
- data/bin/rspec +0 -29
- data/maps/bgnpcgn-chn-Hans-Latn-pinyin.yaml +0 -7503
- data/maps/historic-jpn-Hrkt-Latn-hepburn.yaml +0 -336
- data/maps/icao-gre-Grek-Latn-9303.yaml +0 -101
- data/maps/mext-jpn-Hrkt-Latn-hepburn.yaml +0 -330
- data/maps/mext-jpn-Hrkt-Latn-kunrei.yaml +0 -308
- data/maps/un-jpn-Hrkt-Latn-hepburn.yaml +0 -313
- data/maps/un-jpn-Hrkt-Latn-kunrei.yaml +0 -354
- data/maps/un-mon-Mong-Latn-2013.yaml +0 -80
|
@@ -0,0 +1,168 @@
|
|
|
1
|
+
---
|
|
2
|
+
authority_id: bgnpcgn
|
|
3
|
+
id: 2016
|
|
4
|
+
language: iso-639-2:rue
|
|
5
|
+
source_script: Cyrl
|
|
6
|
+
destination_script: Latn
|
|
7
|
+
name: ROMANIZATION OF RUSYN, BGN/PCGN 2016 System
|
|
8
|
+
alias:
|
|
9
|
+
ogc11122:
|
|
10
|
+
code: rue_Cyrl2Latn_BGN_2016
|
|
11
|
+
description: The BGN/PCGN system for Rusyn was designed for use in romanizing names written in the Rusyn alphabet.
|
|
12
|
+
url: https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20RUSYN.pdf
|
|
13
|
+
creation_date: 2016
|
|
14
|
+
confirmation_date: 2017
|
|
15
|
+
description: |
|
|
16
|
+
The BGN/PCGN system for Rusyn was designed for use in romanizing names written in the Rusyn
|
|
17
|
+
alphabet. There are two primary dialects of the Rusyn language: Carpatho‐Rusyn and Pannonian Rusyn.
|
|
18
|
+
The Rusyn alphabet is almost identical to the Ukrainian alphabet, but contains three characters not
|
|
19
|
+
present in the Ukrainian alphabet: ё, ы, and ъ. These letters are also absent from the alphabet used by
|
|
20
|
+
Pannonian Rusyn. This table applies to both dialects of Rusyn.
|
|
21
|
+
|
|
22
|
+
notes:
|
|
23
|
+
- |
|
|
24
|
+
The letters ё, ы, and ъ are present in the orthography of the Carpatho‐Rusyn variant of the Rusyn
|
|
25
|
+
language. This variant is predominant among Rusyn speakers in Ukraine, Poland, Slovakia, Hungary, and
|
|
26
|
+
Romania. The letters are absent from the orthography of Pannonian Rusyn, which is predominant in
|
|
27
|
+
Serbia and Croatia.
|
|
28
|
+
|
|
29
|
+
- |
|
|
30
|
+
Unicode for Latin‐script characters: Ž/ž (017D, 017E); Č/č (010C, 010D); Š/š (0160, 0161); ’ (0027).
|
|
31
|
+
|
|
32
|
+
- |
|
|
33
|
+
The Romanization columns show only lowercase forms but, when romanizing, uppercase and
|
|
34
|
+
lowercase Roman letters as appropriate should be used.
|
|
35
|
+
|
|
36
|
+
tests:
|
|
37
|
+
# Based on https://ru.wikipedia.org/wiki/Русинский_язык#Примеры_текста
|
|
38
|
+
- source: русиньскый язык
|
|
39
|
+
expected: rusyn'skyj yazyk
|
|
40
|
+
- source: руська бисіда
|
|
41
|
+
expected: rus'ka bysida
|
|
42
|
+
- source: руснацькый язык
|
|
43
|
+
expected: rusnac'kyj yazyk
|
|
44
|
+
- source: руски язик
|
|
45
|
+
expected: rusky yazyk
|
|
46
|
+
- source: |
|
|
47
|
+
Чоловік найчастїше споминать на молоды часы. Є то цалком нормалне.
|
|
48
|
+
Тадь то рокы, кідь зазнаме всякого. І доброго, і планого. В тім часї ся чоловік находить, як кібы в скаралущі.
|
|
49
|
+
Розвивать ся, як цвіт на черешни. Выпхати ся мож з того обалу лем тогды, як прийде час, кідь цалком дозріє.
|
|
50
|
+
Даколи стачіть ся неограбаным способом дотулити білого домику, такой ся пораниш, што ті буде тякнути на цілый жывот.
|
|
51
|
+
А кідь ся народиш в теплї, обколесеный ласков, розвиваш ся в добрых условіях, выпадеш із скаралущі, як міцна істота.
|
|
52
|
+
Такым потім буде і твій далшый жывот. Із добрї заложеным фундаментом. Было бы смішно сі робити надїй, же жывот є лем єдна рівна путь…
|
|
53
|
+
Кібы то так чоловік знав… Кібы ся міг іщі раз народити і піти по тій істій пути…
|
|
54
|
+
expected: |
|
|
55
|
+
Čolovik najčastjiše spomynat' na molody časy. Je to calkom normalne.
|
|
56
|
+
Tad' to roky, kid' zazname vsyakogo. I dobrogo, i planogo. V tim časji sya čolovik nachodyt', yak kiby v skaralušči.
|
|
57
|
+
Rozvyvat' sya, yak cvit na čerešny. Vypchaty sya mož z togo obalu lem togdy, yak pryjde čas, kid' calkom dozrije.
|
|
58
|
+
Dakoly stačit' sya neograbanym sposobom dotulyty bilogo domyku, takoj sya poranyš, što ti bude tyaknuty na cilyj žyvot.
|
|
59
|
+
A kid' sya narodyš v teplji, obkolesenyj laskov, rozvyvaš sya v dobrych usloviyach, vypadeš iz skaralušči, yak micna istota.
|
|
60
|
+
Takym potim bude i tvij dalšyj žyvot. Iz dobrji založenym fundamentom. Bylo by smišno si robyty nadjij, že žyvot je lem jedna rivna put'…
|
|
61
|
+
Kiby to tak čolovik znav… Kiby sya mig išči raz narodyty i pity po tij istij puty…
|
|
62
|
+
# Based on http://www.philology.ru/linguistics3/suprun-89.htm
|
|
63
|
+
- source: |
|
|
64
|
+
Вишло слунко красне, ясне,
|
|
65
|
+
и цму швета розогнало -
|
|
66
|
+
жем желену, били хмарки
|
|
67
|
+
як зоз златом да обцагло.
|
|
68
|
+
expected: |
|
|
69
|
+
Vyšlo slunko krasne, yasne,
|
|
70
|
+
y cmu šveta rozognalo -
|
|
71
|
+
žem želenu, byly chmarky
|
|
72
|
+
yak zoz zlatom da obcaglo.
|
|
73
|
+
- source: шнїг
|
|
74
|
+
expected: šnjig
|
|
75
|
+
- source: жем
|
|
76
|
+
expected: žem
|
|
77
|
+
- source: дзень
|
|
78
|
+
expected: dzen'
|
|
79
|
+
- source: спомнуц
|
|
80
|
+
expected: spomnuc
|
|
81
|
+
- source: крава
|
|
82
|
+
expected: krava
|
|
83
|
+
# Based on https://lingvoforum.net/index.php?topic=43545.0
|
|
84
|
+
- source: дївка
|
|
85
|
+
expected: djivka
|
|
86
|
+
- source: дрыв
|
|
87
|
+
expected: dryv
|
|
88
|
+
- source: фёрд
|
|
89
|
+
expected: fjord
|
|
90
|
+
- source: Ёзеф
|
|
91
|
+
expected: Jozef
|
|
92
|
+
- source: пастырї
|
|
93
|
+
expected: pastyrji
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
map:
|
|
97
|
+
characters:
|
|
98
|
+
"\u0410": "A" # А
|
|
99
|
+
"\u0411": "B" # Б
|
|
100
|
+
"\u0412": "V" # В
|
|
101
|
+
"\u0413": "H" # Г
|
|
102
|
+
"\u0414": "D" # Д
|
|
103
|
+
"\u0415": "E" # Е
|
|
104
|
+
"\u0404": "Je" # Є
|
|
105
|
+
"\u0401": "Jo" # Ё
|
|
106
|
+
"\u0416": "\u017D" # Ж => Ž note[2]
|
|
107
|
+
"\u0417": "Z" # З
|
|
108
|
+
"\u0418": "Y" # И
|
|
109
|
+
"\u0406": "I" # І
|
|
110
|
+
"\u042b": "Y" # Ы
|
|
111
|
+
"\u0407": "Ji" # Ї
|
|
112
|
+
"\u0419": "J" # Й
|
|
113
|
+
"\u041a": "K" # К
|
|
114
|
+
"\u041b": "L" # Л
|
|
115
|
+
"\u041c": "M" # М
|
|
116
|
+
"\u041d": "N" # Н
|
|
117
|
+
"\u041e": "O" # О
|
|
118
|
+
"\u041f": "P" # П
|
|
119
|
+
"\u0420": "R" # Р
|
|
120
|
+
"\u0421": "S" # С
|
|
121
|
+
"\u0422": "T" # Т
|
|
122
|
+
"\u0423": "U" # У
|
|
123
|
+
"\u0424": "F" # Ф
|
|
124
|
+
"\u0425": "Ch" # Х
|
|
125
|
+
"\u0426": "C" # Ц
|
|
126
|
+
"\u0427": "\u010C" # Ч => Č note[2]
|
|
127
|
+
"\u0428": "\u0160" # Ш => Š note[2]
|
|
128
|
+
"\u0429": "\u0160\u010C" # Щ => ŠČ
|
|
129
|
+
"\u042e": "Yu" # Ю
|
|
130
|
+
"\u042f": "Ya" # Я
|
|
131
|
+
"\u042c": "\u0027" # Ь => '
|
|
132
|
+
"\u042a": "\u0027" # Ъ => '
|
|
133
|
+
|
|
134
|
+
"\u0430": "a" # а
|
|
135
|
+
"\u0431": "b" # б
|
|
136
|
+
"\u0432": "v" # в
|
|
137
|
+
"\u0433": "g" # г
|
|
138
|
+
"\u0434": "d" # д
|
|
139
|
+
"\u0435": "e" # е
|
|
140
|
+
"\u0454": "je" # є
|
|
141
|
+
"\u0451": "jo" # ё
|
|
142
|
+
"\u0436": "\u017E" # ж => ž note[2]
|
|
143
|
+
"\u0437": "z" # з
|
|
144
|
+
"\u0438": "y" # и
|
|
145
|
+
"\u0456": "i" # і
|
|
146
|
+
"\u044b": "y" # ы
|
|
147
|
+
"\u0457": "ji" # ї
|
|
148
|
+
"\u0439": "j" # й
|
|
149
|
+
"\u043a": "k" # к
|
|
150
|
+
"\u043b": "l" # л
|
|
151
|
+
"\u043c": "m" # м
|
|
152
|
+
"\u043d": "n" # н
|
|
153
|
+
"\u043e": "o" # о
|
|
154
|
+
"\u043f": "p" # п
|
|
155
|
+
"\u0440": "r" # р
|
|
156
|
+
"\u0441": "s" # с
|
|
157
|
+
"\u0442": "t" # т
|
|
158
|
+
"\u0443": "u" # у
|
|
159
|
+
"\u0444": "f" # ф
|
|
160
|
+
"\u0445": "ch" # х
|
|
161
|
+
"\u0446": "c" # ц
|
|
162
|
+
"\u0447": "\u010D" # ч => č note[2]
|
|
163
|
+
"\u0448": "\u0161" # ш => š note[2]
|
|
164
|
+
"\u0449": "\u0161\u010D" # щ => šč
|
|
165
|
+
"\u044e": "yu" # ю
|
|
166
|
+
"\u044f": "ya" # я
|
|
167
|
+
"\u044c": "\u0027" # ь => '
|
|
168
|
+
"\u044a": "\u0027" # ъ => '
|
|
@@ -1,10 +1,14 @@
|
|
|
1
1
|
---
|
|
2
2
|
authority_id: bgnpcgn
|
|
3
3
|
id: 1947
|
|
4
|
-
language: rus
|
|
4
|
+
language: iso-639-2:rus
|
|
5
5
|
source_script: Cyrl
|
|
6
6
|
destination_script: Latn
|
|
7
7
|
name: ROMANIZATION OF RUSSIAN, BGN/PCGN 1947 System
|
|
8
|
+
alias:
|
|
9
|
+
ogc11122:
|
|
10
|
+
code: rus_Cyrl2Latn_BGN_1947
|
|
11
|
+
description: Russian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 1947 System
|
|
8
12
|
url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/807920/ROMANIZATION_OF_RUSSIAN.pdf
|
|
9
13
|
creation_date: 1947
|
|
10
14
|
confirmation_date: 2019-06
|
|
@@ -102,69 +106,148 @@ tests:
|
|
|
102
106
|
Число открепительных удостоверений, утраченных в окружной избирательной комиссии
|
|
103
107
|
|
|
104
108
|
expected: |
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
|
|
126
|
-
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
|
|
109
|
+
Vybory deputatov Gosudarstvennoy Dumy Federal’nogo Sobraniya Rossiyskoy Federatsii sed’mogo sozyva
|
|
110
|
+
Data golosovaniya: 18.09.2016
|
|
111
|
+
|
|
112
|
+
Naimenovaniye Izbiratel’noy komissii: TSIK Rossii
|
|
113
|
+
|
|
114
|
+
Svodnaya tablitsa rezul’tatov vyborov po federal’nomu izbiratel’nomu okrugu
|
|
115
|
+
|
|
116
|
+
|
|
117
|
+
Chislo izbirateley, vnesennykh v spisok izbirateley na moment okonchaniya golosovaniya
|
|
118
|
+
Chislo izbiratel’nykh byulleteney, poluchennykh uchastkovoy izbiratel’noy komissiyey
|
|
119
|
+
Chislo izbiratel’nykh byulleteney, vydannykh izbiratelyam, progolosovavshim dosrochno
|
|
120
|
+
Chislo izbiratel’nykh byulleteney, vydannykh v pomeshchenii dlya golosovaniya v den’ golosovaniya
|
|
121
|
+
Chislo izbiratel’nykh byulleteney, vydannykh vne pomeshcheniya dlya golosovaniya v den’ golosovaniya
|
|
122
|
+
Chislo pogashennykh izbiratel’nykh byulleteney
|
|
123
|
+
Chislo izbiratel’nykh byulleteney, soderzhashchikhsya v perenosnykh yashchikakh dlya golosovaniya
|
|
124
|
+
Chislo izbiratel’nykh byulleteney, soderzhashchikhsya v statsionarnykh yashchikakh dlya golosovaniya
|
|
125
|
+
Chislo nedeystvitel’nykh izbiratel’nykh byulleteney
|
|
126
|
+
Chislo deystvitel’nykh izbiratel’nykh byulleteney
|
|
127
|
+
Chislo otkrepitel’nykh udostovereniy, poluchennykh uchastkovoy izbiratel’noy komissiyey
|
|
128
|
+
Chislo otkrepitel’nykh udostovereniy, vydannykh na izbiratel’nom uchastke do dnya golosovaniya
|
|
129
|
+
Chislo izbirateley, progolosovavshikh po otkrepitel’nym udostovereniyam na izbiratel’nom uchastke
|
|
130
|
+
Chislo pogashennykh neispol’zovannykh otkrepitel’nykh udostovereniy
|
|
131
|
+
Chislo otkrepitel’nykh udostovereniy, vydannykh izbiratelyam territorial’noy izbiratel’noy komissiyey
|
|
132
|
+
Chislo utrachennykh otkrepitel’nykh udostovereniy
|
|
133
|
+
Chislo utrachennykh izbiratel’nykh byulleteney
|
|
134
|
+
Chislo izbiratel’nykh byulleteney, ne uchtennykh pri poluchenii
|
|
131
135
|
1. VSEROSSIYSKAYA POLITICHESKAYA PARTIYA "RODINA"
|
|
132
|
-
2.
|
|
133
|
-
3.
|
|
134
|
-
4.
|
|
135
|
-
5.
|
|
136
|
-
6.
|
|
137
|
-
7.
|
|
138
|
-
8.
|
|
139
|
-
9.
|
|
140
|
-
10.
|
|
141
|
-
11.
|
|
142
|
-
12.
|
|
143
|
-
13.
|
|
144
|
-
14.
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
|
|
149
|
-
|
|
150
|
-
|
|
151
|
-
|
|
152
|
-
|
|
136
|
+
2. Politicheskaya partiya KOMMUNISTICHESKAYA PARTIYA KOMMUNISTY ROSSII
|
|
137
|
+
3. Politicheskaya partiya "Rossiyskaya partiya pensionerov za spravedlivost’"
|
|
138
|
+
4. Vserossiyskaya politicheskaya partiya "YEDINAYA ROSSIYA"
|
|
139
|
+
5. Politicheskaya partiya "Rossiyskaya ekologicheskaya partiya "Zelenyye"
|
|
140
|
+
6. Politicheskaya partiya "Grazhdanskaya Platforma"
|
|
141
|
+
7. Politicheskaya partiya LDPR - Liberal’no-demokraticheskaya partiya Rossii
|
|
142
|
+
8. Politicheskaya partiya "Partiya narodnoy svobody" (PARNAS)
|
|
143
|
+
9. Vserossiyskaya politicheskaya partiya "PARTIYA ROSTA"
|
|
144
|
+
10. Obshchestvennaya organizatsiya Vserossiyskaya politicheskaya partiya "Grazhdanskaya Sila"
|
|
145
|
+
11. Politicheskaya partiya "Rossiyskaya ob"yedinennaya demokraticheskaya partiya "YABLOKO"
|
|
146
|
+
12. Politicheskaya partiya "KOMMUNISTICHESKAYA PARTIYA ROSSIYSKOY FEDERATSII"
|
|
147
|
+
13. Politicheskaya partiya "PATRIOTY ROSSII"
|
|
148
|
+
14. Politicheskaya partiya SPRAVEDLIVAYA ROSSIYA
|
|
149
|
+
|
|
150
|
+
Dannyye okruzhnykh izbiratel’nykh komissiy o chisle otkrepitel’nykh udostovereniy
|
|
151
|
+
|
|
152
|
+
|
|
153
|
+
Chislo otkrepitel’nykh udostovereniy, poluchennykh okruzhnoy izbiratel’noy komissiyey
|
|
154
|
+
Chislo otkrepitel’nykh udostovereniy, vydannykh territorial’nym izbiratel’nym komissiyam
|
|
155
|
+
Chislo neispol’zovannykh otkrepitel’nykh udostovereniy, pogashennykh okruzhnoy izbiratel’noy komissiyey
|
|
156
|
+
Chislo otkrepitel’nykh udostovereniy, utrachennykh v okruzhnoy izbiratel’noy komissii
|
|
157
|
+
- source: ДЛИННОЕ ПОКРЫВАЛО
|
|
158
|
+
expected: DLINNOYE POKRYVALO
|
|
159
|
+
- source: Еловая шишка
|
|
160
|
+
expected: Yelovaya shishka
|
|
161
|
+
- source: ЕЛОВАЯ ШИШКА
|
|
162
|
+
expected: YELOVAYA SHISHKA
|
|
163
|
+
- source: Длинное покрывало
|
|
164
|
+
expected: Dlinnoye pokryvalo
|
|
165
|
+
- source: В лесу еловые шишки
|
|
166
|
+
expected: V lesu yelovyye shishki
|
|
167
|
+
- source: OН ВИДЕЛ ЕЁ В ПЕРВЫЙ РАЗ
|
|
168
|
+
expected: ON VIDEL YEYË V PERVYY RAZ
|
|
169
|
+
- source: Ёж колючий
|
|
170
|
+
expected: Yëzh kolyuchiy
|
|
171
|
+
- source: ЁЖ КОЛЮЧИЙ
|
|
172
|
+
expected: YËZH KOLYUCHIY
|
|
173
|
+
- source: Он видел её в первый раз
|
|
174
|
+
expected: On videl yeyë v pervyy raz
|
|
175
|
+
- source: У ёжа колючки
|
|
176
|
+
expected: U yëzha kolyuchki
|
|
177
|
+
- source: ЙА Йа йа
|
|
178
|
+
expected: Y·A Y·a y·a
|
|
179
|
+
- source: ЫУ Ыу ыу
|
|
180
|
+
expected: Y·U Y·u y·u
|
|
181
|
+
- source: ОЫ Оы оы
|
|
182
|
+
expected: O·Y O·y o·y
|
|
183
|
+
- source: ОЫУ Оыу оыу
|
|
184
|
+
expected: O·Y·U O·y·u o·y·u
|
|
185
|
+
- source: СЭ Сэ сэ
|
|
186
|
+
expected: S·E S·e s·e
|
|
187
|
+
- source: ТС тс Тс тС
|
|
188
|
+
expected: T·S t·s T·s t·S
|
|
189
|
+
- source: ШЧ шч Шч шЧ
|
|
190
|
+
expected: SH·CH sh·ch Sh·ch sh·Ch
|
|
153
191
|
|
|
154
192
|
map:
|
|
155
193
|
rules:
|
|
156
|
-
- pattern: ([
|
|
157
|
-
result: "
|
|
158
|
-
- pattern: \
|
|
159
|
-
result:
|
|
160
|
-
- pattern: ([
|
|
161
|
-
result: "
|
|
162
|
-
- pattern:
|
|
163
|
-
result: "
|
|
164
|
-
- pattern: \
|
|
165
|
-
result:
|
|
166
|
-
- pattern:
|
|
167
|
-
result: "
|
|
194
|
+
- pattern: (?<=[АаЕеЁёИиОоУуЫыЭэЮюЯяЙйЪъЬь])\u0401 # Ё after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
|
|
195
|
+
result: "Y\u00eb"
|
|
196
|
+
- pattern: (?<=[АаЕеЁёИиОоУуЫыЭэЮюЯяЙйЪъЬь])\u0451 # ё after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
|
|
197
|
+
result: "y\u00eb"
|
|
198
|
+
- pattern: (?<=[АаЕеЁёИиОоУуЫыЭэЮюЯяЙйЪъЬь])\u0415 # Е after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
|
|
199
|
+
result: "Y\u0415"
|
|
200
|
+
- pattern: \b\u0415 # Е initially
|
|
201
|
+
result: "Y\u0435"
|
|
202
|
+
- pattern: (?<=[АаЕеЁёИиОоУуЫыЭэЮюЯяЙйЪъЬь])\u0435 # е after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
|
|
203
|
+
result: "y\u0435"
|
|
204
|
+
- pattern: \b\u0435 # е initially
|
|
205
|
+
result: "y\u0435"
|
|
206
|
+
- pattern: (?<=[АаЕеЁёИиОоУуЫыЭэЮюЯяЙйЪъЬь])\u0401 # Ё after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
|
|
207
|
+
result: "Y\u00eb"
|
|
208
|
+
- pattern: \b\u0401
|
|
209
|
+
result: "Y\u00eb"
|
|
210
|
+
- pattern: (?<=[АаЕеЁёИиОоУуЫыЭэЮюЯяЙйЪъЬь])\u0451 # ё after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
|
|
211
|
+
result: "y\u00eb"
|
|
212
|
+
- pattern: \b\u0451
|
|
213
|
+
result: "y\u00eb"
|
|
214
|
+
- pattern: \u0419(?=[АаУуЫыЭэ]) # Й before а, у, ы, or э
|
|
215
|
+
result: "Y\u00b7"
|
|
216
|
+
- pattern: \u0439(?=[АаУуЫыЭэ]) # й before а, у, ы, or э
|
|
217
|
+
result: "y\u00b7"
|
|
218
|
+
- pattern: (?<=[АаЕеЁёИиОоУуЫыЭэЮюЯя])\u042b(?=[АаУуЫыЭэ]) # Ы after any vowel character and before а, у, ы, or э
|
|
219
|
+
result: "\u00b7Y\u00b7"
|
|
220
|
+
- pattern: (?<=[АаЕеЁёИиОоУуЫыЭэЮюЯя])\u044b(?=[АаУуЫыЭэ]) # ы after any vowel character and before а, у, ы, or э
|
|
221
|
+
result: "\u00b7y\u00b7"
|
|
222
|
+
- pattern: \u042b(?=[АаУуЫыЭэ]) # Ы before а, у, ы, or э
|
|
223
|
+
result: "Ы\u00b7"
|
|
224
|
+
- pattern: \u044b(?=[АаУуЫыЭэ]) # ы before а, у, ы, or э
|
|
225
|
+
result: "ы\u00b7"
|
|
226
|
+
- pattern: (?<=[Оо])\u042b # Ы after о
|
|
227
|
+
result: "\u00b7Y"
|
|
228
|
+
- pattern: (?<=[Оо])\u044b # ы after о
|
|
229
|
+
result: "\u00b7y"
|
|
230
|
+
- pattern: \b\u0401
|
|
231
|
+
result: "Y\u00eb"
|
|
232
|
+
- pattern: \b\u0451
|
|
233
|
+
result: "y\u00eb"
|
|
234
|
+
- pattern: (?<=[БбВвГгДдЖжЗзКкЛлМмНнПпРрСсТтФфХхЦцЧчШшЩщ])\u042d # Э after any consonant character except й
|
|
235
|
+
result: "\u00b7E"
|
|
236
|
+
- pattern: (?<=[БбВвГгДдЖжЗзКкЛлМмНнПпРрСсТтФфХхЦцЧчШшЩщ])\u044d # э after any consonant character except й
|
|
237
|
+
result: "\u00b7e"
|
|
238
|
+
- pattern: (Т|т)(С|с) # тс => t·s
|
|
239
|
+
result: "\\1\u00b7\\2"
|
|
240
|
+
- pattern: (Ш|ш)(Ч|ч) # шч => sh·ch
|
|
241
|
+
result: "\\1\u00b7\\2"
|
|
242
|
+
|
|
243
|
+
postrules:
|
|
244
|
+
|
|
245
|
+
#YE
|
|
246
|
+
- pattern: "((?<=[[:upper:]])Ye(?=[[:upper:]])?|(?<=[[:upper:]])?Ye(?=[[:upper:]]))"
|
|
247
|
+
result: "YE"
|
|
248
|
+
#YË
|
|
249
|
+
- pattern: "((?<=[[:upper:]])Yë(?=[[:upper:]])?|(?<=[[:upper:]])?Yë(?=[[:upper:]]))"
|
|
250
|
+
result: "YË"
|
|
168
251
|
|
|
169
252
|
characters:
|
|
170
253
|
"\u0410": "A"
|
|
@@ -173,7 +256,7 @@ map:
|
|
|
173
256
|
"\u0413": "G"
|
|
174
257
|
"\u0414": "D"
|
|
175
258
|
"\u0415": "E"
|
|
176
|
-
"\
|
|
259
|
+
"\u0401": "\u00cb" # Ё
|
|
177
260
|
"\u0416": "Zh"
|
|
178
261
|
"\u0417": "Z"
|
|
179
262
|
"\u0418": "I"
|
|
@@ -194,9 +277,9 @@ map:
|
|
|
194
277
|
"\u0427": "Ch"
|
|
195
278
|
"\u0428": "Sh"
|
|
196
279
|
"\u0429": "Shch"
|
|
197
|
-
"\u042a": "\""
|
|
280
|
+
"\u042a": "\"" # Ъ
|
|
198
281
|
"\u042b": "Y"
|
|
199
|
-
"\u042c": "\u2019"
|
|
282
|
+
"\u042c": "\u2019" # Ь => ’
|
|
200
283
|
"\u042d": "E"
|
|
201
284
|
"\u042e": "Yu"
|
|
202
285
|
"\u042f": "Ya"
|
|
@@ -205,6 +288,8 @@ map:
|
|
|
205
288
|
"\u0432": "v"
|
|
206
289
|
"\u0433": "g"
|
|
207
290
|
"\u0434": "d"
|
|
291
|
+
"\u0435": "e"
|
|
292
|
+
"\u0451": "\u00eb" # ё
|
|
208
293
|
"\u0436": "zh"
|
|
209
294
|
"\u0437": "z"
|
|
210
295
|
"\u0438": "i"
|
|
@@ -225,9 +310,9 @@ map:
|
|
|
225
310
|
"\u0447": "ch"
|
|
226
311
|
"\u0448": "sh"
|
|
227
312
|
"\u0449": "shch"
|
|
228
|
-
"\u044a": "\""
|
|
313
|
+
"\u044a": "\"" # ъ
|
|
229
314
|
"\u044b": "y"
|
|
230
|
-
"\u044c": "\u2019"
|
|
315
|
+
"\u044c": "\u2019" # ь => ’
|
|
231
316
|
"\u044d": "e"
|
|
232
317
|
"\u044e": "yu"
|
|
233
318
|
"\u044f": "ya"
|
|
@@ -0,0 +1,170 @@
|
|
|
1
|
+
---
|
|
2
|
+
authority_id: bgnpcgn
|
|
3
|
+
id: 2005
|
|
4
|
+
language: iso-639-2:srp
|
|
5
|
+
source_script: Cyrl
|
|
6
|
+
destination_script: Latn
|
|
7
|
+
name: ROMANIZATION OF SERBIAN, BGN/PCGN 2005 System
|
|
8
|
+
alias:
|
|
9
|
+
ogc11122:
|
|
10
|
+
code: srp_Cyrl2Latn_BGN_2005
|
|
11
|
+
description: Serbian Cyrillic Table of Correspondences US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 2005
|
|
12
|
+
url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816783/TABLE_OF_CORRESPONDENCES_FOR_SERBIAN.pdf
|
|
13
|
+
creation_date: 2005
|
|
14
|
+
confirmation_date: 2019-06
|
|
15
|
+
description: |
|
|
16
|
+
The tabulation below reflects the Serbian Cyrillic alphabet and the standard Roman script equivalents
|
|
17
|
+
used in both Serbia and Montenegro.
|
|
18
|
+
|
|
19
|
+
notes:
|
|
20
|
+
- The Serbian Cyrillic lowercase italic Д may sometimes be seen as g.
|
|
21
|
+
There is no specific Unicode encoding for this variant form so a comparable character
|
|
22
|
+
has been used here for illustrative purposes.
|
|
23
|
+
|
|
24
|
+
- The digraph dj(Dj) will occasionally be found as an alternative form of đ(Đ).
|
|
25
|
+
|
|
26
|
+
- The Serbian Cyrillic lowercase italic П may sometimes be seen as ӣ.
|
|
27
|
+
There is no specific Unicode encoding for this variant form so a comparable character
|
|
28
|
+
has been used here for illustrative purposes.
|
|
29
|
+
|
|
30
|
+
- The Serbian Cyrillic lowercase italic Т may sometimes be seen as w.
|
|
31
|
+
There is no specific Unicode encoding for this variant form so a comparable character
|
|
32
|
+
has been used here for illustrative purposes.
|
|
33
|
+
|
|
34
|
+
- |
|
|
35
|
+
An inventory of letter-diacritic combinations, with their Unicode encoding,
|
|
36
|
+
in addition to the unmodified letters of the basic Roman script is:
|
|
37
|
+
| Đ (U+0110) | đ (U+0111) |
|
|
38
|
+
| Ž (U+017D) | ž (U+017E) |
|
|
39
|
+
| Lj (U+01C8)* | lj (U+01C9)* |
|
|
40
|
+
| Ć (U+0106) | ć (U+0107) |
|
|
41
|
+
| Dž (U+01C5)* | dž (U+01C6)* |
|
|
42
|
+
| Š (U+0160) | š (U+0161) |
|
|
43
|
+
* Note that these characters can also be reproduced with individual letters (e.g. l+j).
|
|
44
|
+
|
|
45
|
+
- The Roman-script columns show only lowercase forms but, when applying the table,
|
|
46
|
+
uppercase and lowercase Roman letters as appropriate should be used.
|
|
47
|
+
|
|
48
|
+
tests:
|
|
49
|
+
- source: Шупља Стена
|
|
50
|
+
expected: Šuplja Stena
|
|
51
|
+
- source: Чукарица
|
|
52
|
+
expected: Čukarica
|
|
53
|
+
- source: Црна Трава
|
|
54
|
+
expected: Crna Trava
|
|
55
|
+
- source: Херцег Нови
|
|
56
|
+
expected: Herceg Novi
|
|
57
|
+
- source: Улцињ
|
|
58
|
+
expected: Ulcinj
|
|
59
|
+
- source: Ужице
|
|
60
|
+
expected: Užice
|
|
61
|
+
- source: Тресаначка Река
|
|
62
|
+
expected: Tresanačka Reka
|
|
63
|
+
- source: Сјеница
|
|
64
|
+
expected: Sjenica
|
|
65
|
+
- source: Рожаје
|
|
66
|
+
expected: Rožaje
|
|
67
|
+
- source: Пљевља
|
|
68
|
+
expected: Pljevlja
|
|
69
|
+
- source: Оџаци
|
|
70
|
+
expected: Odžaci
|
|
71
|
+
- source: Никшић
|
|
72
|
+
expected: Nikšić
|
|
73
|
+
- source: Медвеђа
|
|
74
|
+
expected: Medveđa
|
|
75
|
+
- source: Лозница
|
|
76
|
+
expected: Loznica
|
|
77
|
+
- source: Књажевац
|
|
78
|
+
expected: Knjaževac
|
|
79
|
+
- source: Зрењанин
|
|
80
|
+
expected: Zrenjanin
|
|
81
|
+
- source: Житорађа
|
|
82
|
+
expected: Žitorađa
|
|
83
|
+
- source: Ервеник
|
|
84
|
+
expected: Ervenik
|
|
85
|
+
- source: Доње Љупче
|
|
86
|
+
expected: Donje Ljupče
|
|
87
|
+
- source: Гусиње
|
|
88
|
+
expected: Gusinje
|
|
89
|
+
- source: ГУСИЊЕ
|
|
90
|
+
expected: GUSINJE
|
|
91
|
+
- source: Врњачка Бања
|
|
92
|
+
expected: Vrnjačka Banja
|
|
93
|
+
- source: Бијело Поље
|
|
94
|
+
expected: Bijelo Polje
|
|
95
|
+
- source: Алибунар
|
|
96
|
+
expected: Alibunar
|
|
97
|
+
|
|
98
|
+
map:
|
|
99
|
+
postrules:
|
|
100
|
+
#LJ
|
|
101
|
+
- pattern: "((?<=[[:upper:]])Lj(?=[[:upper:]])?|(?<=[[:upper:]])?Lj(?=[[:upper:]]))"
|
|
102
|
+
result: "LJ"
|
|
103
|
+
#NJ
|
|
104
|
+
- pattern: "((?<=[[:upper:]])Nj(?=[[:upper:]])?|(?<=[[:upper:]])?Nj(?=[[:upper:]]))"
|
|
105
|
+
result: "NJ"
|
|
106
|
+
#DŽ
|
|
107
|
+
- pattern: "((?<=[[:upper:]])Dž(?=[[:upper:]])?|(?<=[[:upper:]])?Dž(?=[[:upper:]]))"
|
|
108
|
+
result: "DŽ"
|
|
109
|
+
|
|
110
|
+
characters:
|
|
111
|
+
"\u0410": "A"
|
|
112
|
+
"\u0411": "B"
|
|
113
|
+
"\u0412": "V"
|
|
114
|
+
"\u0413": "G"
|
|
115
|
+
"\u0414": "D"
|
|
116
|
+
"\u0402": "\u0110" # Đ
|
|
117
|
+
"\u0415": "E"
|
|
118
|
+
"\u0416": "\u005a\u030c" # Ž
|
|
119
|
+
"\u0417": "Z"
|
|
120
|
+
"\u0418": "I"
|
|
121
|
+
"\u0408": "J"
|
|
122
|
+
"\u041A": "K"
|
|
123
|
+
"\u041B": "L"
|
|
124
|
+
"\u0409": "Lj"
|
|
125
|
+
"\u041C": "M"
|
|
126
|
+
"\u041D": "N"
|
|
127
|
+
"\u040A": "Nj"
|
|
128
|
+
"\u041E": "O"
|
|
129
|
+
"\u041F": "P"
|
|
130
|
+
"\u0420": "R"
|
|
131
|
+
"\u0421": "S"
|
|
132
|
+
"\u0422": "T"
|
|
133
|
+
"\u040B": "\u0043\u0301" # Ć
|
|
134
|
+
"\u0423": "U"
|
|
135
|
+
"\u0424": "F"
|
|
136
|
+
"\u0425": "H"
|
|
137
|
+
"\u0426": "C"
|
|
138
|
+
"\u0427": "\u0043\u030c" # Č
|
|
139
|
+
"\u040F": "D\u007a\u030c" # Dž
|
|
140
|
+
"\u0428": "\u0053\u030c" # Š
|
|
141
|
+
"\u0430": "a"
|
|
142
|
+
"\u0431": "b"
|
|
143
|
+
"\u0432": "v"
|
|
144
|
+
"\u0433": "g"
|
|
145
|
+
"\u0434": "d"
|
|
146
|
+
"\u0452": "\u0111" # đ
|
|
147
|
+
"\u0435": "e"
|
|
148
|
+
"\u0436": "\u007a\u030c" # ž
|
|
149
|
+
"\u0437": "z"
|
|
150
|
+
"\u0438": "i"
|
|
151
|
+
"\u0458": "j"
|
|
152
|
+
"\u043A": "k"
|
|
153
|
+
"\u043B": "l"
|
|
154
|
+
"\u0459": "lj"
|
|
155
|
+
"\u043C": "m"
|
|
156
|
+
"\u043D": "n"
|
|
157
|
+
"\u045A": "nj"
|
|
158
|
+
"\u043E": "o"
|
|
159
|
+
"\u043F": "p"
|
|
160
|
+
"\u0440": "r"
|
|
161
|
+
"\u0441": "s"
|
|
162
|
+
"\u0442": "t"
|
|
163
|
+
"\u045B": "\u0063\u0301" # ć́
|
|
164
|
+
"\u0443": "u"
|
|
165
|
+
"\u0444": "f"
|
|
166
|
+
"\u0445": "h"
|
|
167
|
+
"\u0446": "c"
|
|
168
|
+
"\u0447": "\u0063\u030c" # č
|
|
169
|
+
"\u045F": "d\u007a\u030c" # dž
|
|
170
|
+
"\u0448": "\u0073\u030c" # š
|