interscript-maps 2.1.0rc4 → 2.1.0

data/maps/ses-ara-Arab-Latn-1930.imp

@@ -1,15 +1,58 @@
 metadata {
-  authority_id: ses
+  authority_id: ungegn
   id: 1930
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: Survey of Egypt Romanization
+  name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
   url: http://www.eki.ee/wgrs/rom1_ar.pdf
   creation_date: 1930
   confirmation_date: 2018-06
   description: |
-    The Survey of Egypt System (SES) of Romanization.
+    The current United Nations recommended romanization
+    system was approved in 2017 (resolution XI/3), based on
+    the system adopted by Arabic experts at the conference
+    held in Beirut in 2007, the Unified Arabic
+    Transliteration System, taking into account the
+    practical amendments and corrections carried out and
+    agreed upon by the representatives of the Arabic-
+    speaking countries at the Fourth Arab Conference on
+    Geographical Names, held in Beirut in 2008, and some
+    clarifications and amendments agreed in Riyadh in 20171.
+    Previously, the United Nations had approved a
+    romanization system in 1972 (resolution II/8), based on the
+    system adopted by Arabic experts at the conference
+    held at Beirut in 1971 with the practical amendments carried out
+    and agreed upon by the representatives of the Arabic-speaking
+    countries at their conference. The table was published in volume
+    II of the conference report.
+    In UN resolution XI/3 it is specifically stated that the
+    system was recommended for the “romanization of the
+    geographical names within those Arabic-speaking countries
+    where this system is officially adopted”. There is
+    evidence of its partial implementation in Jordan, Oman and
+    Saudi Arabia. The UNGEGN Working Group on Romanization
+    Systems intends to continue monitoring the UN system’s
+    implementation across Arabic-speaking countries.
+    In some countries there exist local romanization schemes
+    or practices. The geographical names of Algeria, Djibouti,
+    Mauritania, Morocco and Tunisia are generally rendered in
+    the traditional manner which conforms to the principles of
+    the French orthography.
+    The previous UN-approved system is still found in
+    considerable international usage.
+    Arabic is written from right to left. The Arabic script
+    usually omits vowel points and diacritical marks from
+    writing which makes it difficult to obtain uniform results
+    in the romanization of Arabic. It is essential to identify
+    correctly the words which appear in any particular name
+    and to know the standard Arabic-script spelling including
+    the relevant vowels. One must also take into account
+    dialectal and idiosyncratic deviations. The romanization
+    is generally reversible though there may be some ambiguous
+    letter sequences (dh, kh, sh, th) which may also point to
+    combinations of Arabic characters in addition to the
+    respective single characters.
   notes:
     - |
       The Survey of Egypt System (SES) of romanization has the following correspondences with
@@ -86,20 +129,20 @@ stage {
 
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "el-t" # الت
-    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), any(["el-th", "el-t"]) # الث
-    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "el-d" # الد
-    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), any(["el-dh", "el-z"]) # الذ
-    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "el-r" # الر
-    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "el-z" # الز
-    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), any(["el-s", "el-c"]) # الس
-    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "el-sh" # الش
-    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "el-ṣ" # الص
-    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "el-ḍ" # الض
-    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "el-ṭ" # الط
-    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), any(["el-ẓ", "el-d"]) # الظ
-    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "el-l" # الل
-    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "el-n" # الن
+    sub boundary + "\u0627\u0644\u062a", "el-t" # الت
+    sub boundary + "\u0627\u0644\u062b", any(["el-th", "el-t"]) # الث
+    sub boundary + "\u0627\u0644\u062f", "el-d" # الد
+    sub boundary + "\u0627\u0644\u0630", any(["el-dh", "el-z"]) # الذ
+    sub boundary + "\u0627\u0644\u0631", "el-r" # الر
+    sub boundary + "\u0627\u0644\u0632", "el-z" # الز
+    sub boundary + "\u0627\u0644\u0633", any(["el-s", "el-c"]) # الس
+    sub boundary + "\u0627\u0644\u0634", "el-sh" # الش
+    sub boundary + "\u0627\u0644\u0635", "el-ṣ" # الص
+    sub boundary + "\u0627\u0644\u0636", "el-ḍ" # الض
+    sub boundary + "\u0627\u0644\u0637", "el-ṭ" # الط
+    sub boundary + "\u0627\u0644\u0638", any(["el-ẓ", "el-d"]) # الظ
+    sub boundary + "\u0627\u0644\u0644", "el-l" # الل
+    sub boundary + "\u0627\u0644\u0646", "el-n" # الن
 
 
     # shadda

data/maps/un-amh-Ethi-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:amh
   source_script: Ethi
   destination_script: Latn
-  name: Romanization of Amharic -- UNGEGN (2016)
+  name: ROMANIZATION OF AMHARIC -- UNGEGN 2016 System
   url: http://www.eki.ee/wgrs/rom1_am.pdf
   creation_date: 1967
   confirmation_date: 2016-03

data/maps/un-ara-Arab-Latn-1971.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 1971
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Arabic -- Beirut system (1971)
+  name: 1971 "Beirut system"
   url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/2nd-uncsgn-docs/E_Conf61_4_Add1_e.pdf
   creation_date: 1971
   confirmation_date: 2018-06
@@ -85,10 +85,10 @@ stage {
   parallel {
 
     # sun letters
-    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "at͟h t͟h" # الث
-    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "ad͟h d͟h" # الذ
-    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "as͟h s͟h" # الش
-    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az͟h z͟h" # الظ
+    sub boundary + "\u0627\u0644\u062b", "at͟h t͟h" # الث
+    sub boundary + "\u0627\u0644\u0630", "ad͟h d͟h" # الذ
+    sub boundary + "\u0627\u0644\u0634", "as͟h s͟h" # الش
+    sub boundary + "\u0627\u0644\u0638", "az͟h z͟h" # الظ
 
     # shadda
     sub "\u062e\u0651", "k͟hk͟h" # خ

data/maps/un-ara-Arab-Latn-1972.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 1972
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Arabic -- UNGEGN (1972)
+  name: ROMANIZATION OF ARABIC -- UNGEGN 1972 System
   url: http://www.eki.ee/wgrs/obs_rom_vers/rom1_ar_v4_0.pdf
   creation_date: 1972
   confirmation_date: 2018-06
@@ -107,9 +107,9 @@ stage {
   # CHARACTERS
   parallel {
 
-    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "aş ş" # الص
-    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aḑ ḑ" # الض
-    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0635", "aş ş" # الص
+    sub boundary + "\u0627\u0644\u0636", "aḑ ḑ" # الض
+    sub boundary + "\u0627\u0644\u0637", "aţ ţ" # الط
 
     sub "\u062d\u0651", "ḩḩ" # ح
     sub "\u0635\u0651", "şş" # ص

data/maps/un-ara-Arab-Latn-2017.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 2017
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Arabic -- Unified Arabic Transliteration System (2017)
+  name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
   url: http://www.eki.ee/wgrs/rom1_ar.pdf
   creation_date: 2017
   confirmation_date: 2018-06
@@ -141,20 +141,20 @@ stage {
     # (B) Marks doubling of the consonant.
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "at t" # الت
-    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "ath th" # الث
-    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
-    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "adh dh" # الذ
-    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "ar r" # الر
-    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "az z" # الز
-    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "as s" # الس
-    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "ash sh" # الش
-    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "as̱ s̱" # الص
-    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aḏ ḏ" # الض
-    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aṯ ṯ" # الط
-    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "ad͟h d͟h" # الظ
-    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
-    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
+    sub boundary + "\u0627\u0644\u062a", "at t" # الت
+    sub boundary + "\u0627\u0644\u062b", "ath th" # الث
+    sub boundary + "\u0627\u0644\u062f", "ad d" # الد
+    sub boundary + "\u0627\u0644\u0630", "adh dh" # الذ
+    sub boundary + "\u0627\u0644\u0631", "ar r" # الر
+    sub boundary + "\u0627\u0644\u0632", "az z" # الز
+    sub boundary + "\u0627\u0644\u0633", "as s" # الس
+    sub boundary + "\u0627\u0644\u0634", "ash sh" # الش
+    sub boundary + "\u0627\u0644\u0635", "as̱ s̱" # الص
+    sub boundary + "\u0627\u0644\u0636", "aḏ ḏ" # الض
+    sub boundary + "\u0627\u0644\u0637", "aṯ ṯ" # الط
+    sub boundary + "\u0627\u0644\u0638", "ad͟h d͟h" # الظ
+    sub boundary + "\u0627\u0644\u0644", "al l" # الل
+    sub boundary + "\u0627\u0644\u0646", "an n" # الن
 
     # TODO: shorten this fragment
     # ta' marboota

data/maps/un-asm-Beng-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ben
   source_script: Beng
   destination_script: Latn
-  name: Romanization of Assamese -- UNGEGN 4.0
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Assamese Romanization, Version 4.0
   url: https://www.eki.ee/wgrs/rom1_as.htm
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-bel-Cyrl-Latn-2007.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Belarusian geographic names (2007)
+  name: National System of Geographic Names Transmission into Roman Alphabet in Belarus
   url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/9th-uncsgn-docs/crp/9th_UNCSGN_e-conf-98-crp-21.pdf
   creation_date: 2007
   description: |
@@ -16,7 +16,7 @@ metadata {
     Republic of Belarus in letters of the Latin alphabet
 
     Based on the Regulation on the State Property Committee of the Republic of Belarus,
-    approved by the Decree of the Council of Ministers of the Republic of Belarus dated July 29, 2006
+    approved by the Decree of the Council of Ministers of the Republic of Belarusdated July 29, 2006
     No. 958 "Issues of the State Committee on Property of the Republic of Belarus"
 }
 

data/maps/un-ben-Beng-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ben
   source_script: Beng
   destination_script: Latn
-  name: Romanization of Bengali -- UNGEGN 4.0
+  name: Bengali Romanization, Version 4.0
   url: http://www.eki.ee/wgrs/rom1_bn.htm
   creation_date: 2016
   description: |

data/maps/un-ell-Grek-Latn-1987-phonetic.imp

@@ -4,16 +4,12 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: Romanization of Greek 1.0 (Phonetic transcription)
+  name: UNGEGN Greek v1.0, Fifth United Nations Conference on the Standardization of Geographical Names. Writing Systems and Guides to Pronunciation Romanization > Conversion of the Greek alphabet into Latin characters. Paper submitted by Greece and Cyprus.
   url: http://www.eki.ee/wgrs/rom1_el.htm
   creation_date: 1987
   description: |
     UNGEGN Romanization table for Greek: Phonetic transcription
 
-    UNGEGN Greek v1.0, Fifth United Nations Conference on the Standardization of
-    Geographical Names. Writing Systems and Guides to Pronunciation Romanization
-    > Conversion of the Greek alphabet into Latin characters. Paper submitted by
-    Greece and Cyprus.
 
   notes:
     - Also included in ISO 843:1997, Annex B, Column 5, and ELOT 743:1982, column 5.

data/maps/un-ell-Grek-Latn-1987-tl.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: Romanization of Greek -- UNGEGN 4.0 (transliteration)
+  name: UNGEGN Greek v4.0
   url: http://www.eki.ee/wgrs/rom1_el.htm
   creation_date: 1987
   description: |

data/maps/un-ell-Grek-Latn-1987-ts.imp

@@ -1,10 +1,10 @@
 metadata {
   authority_id: un
-  id: 1987-ts
+  id: 1987-tl
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: Romanization of Greek -- UNGEGN 4.0 (transcription)
+  name: UNGEGN Greek v4.0
   url: http://www.eki.ee/wgrs/rom1_el.htm
   creation_date: 1987
   description: |

data/maps/un-guj-Gujr-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:guj
   source_script: Gujr
   destination_script: Latn
-  name: Romanization of Gujarati -- UNGEGN 4.0
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Gujarati Romanization Version 4.0
   url: https://www.eki.ee/wgrs/rom1_gu.htm
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-hin-Deva-Latn-2016.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 2016
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: Romanization of Hindi -- UNGEGN 4.0
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Hindi Romanization, 1972
   url: https://www.eki.ee/wgrs/rom1_hi.pdf
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-kan-Kana-Latn-2016.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 2016
   language: iso-639-2:kan
   source_script: Kana
   destination_script: Latn
-  name: Romanization of Kannada -- UNGEGN 4.0
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Kannada Romanization, 1972
   url: https://www.eki.ee/wgrs/rom1_kn.pdf
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-mal-Mlym-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mal
   source_script: Mlym
   destination_script: Latn
-  name: Romanization of Malayalam -- UNGEGN 4.0
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Malayalam Romanization Version 4.0
   url: https://www.eki.ee/wgrs/rom1_ml.htm
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-mar-Deva-Latn-2016.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 2016
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: Romanization of Marathi -- UNGEGN 4.0
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Marathi Romanization, 1972
   url: https://www.eki.ee/wgrs/rom1_mr.pdf
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-mon-Mong-Latn-general-2013.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mon
   source_script: Mong
   destination_script: Latn
-  name: Romanization of Mongolian in China -- UNGEGN 4.0
+  name: Mongolian Romanization in China, Version 4.0 (general)
   url: http://www.eki.ee/wgrs/rom1_mnc.htm
   creation_date: 2013-09
   description: |

data/maps/un-mon-Mong-Latn-phonetic-2013.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mon
   source_script: Mong
   destination_script: Latn
-  name: Romanization of Mongolian in China -- UNGEGN 4.0 (phonetic)
+  name: Mongolian Romanization in China, Version 4.0 (phonetic)
   url: http://www.eki.ee/wgrs/rom1_mnc.htm
   creation_date: 2013-09
   description: |

data/maps/un-nep-Deva-Latn-1972.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 1972
   language: iso-639-2:nep
   source_script: Deva
   destination_script: Latn
-  name: Romanization of Nepali (1972)
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Nepali Romanization, 1972
   url: https://www.eki.ee/wgrs/v3_0/rom1_ne.pdf
   creation_date: 1972
   confirmation_date: 2010

data/maps/un-nep-Deva-Latn-2013.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 2013
   language: iso-639-2:nep
   source_script: Deva
   destination_script: Latn
-  name: Romanization of Nepali (2013)
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Nepali Romanization, 1972
   url: https://www.eki.ee/wgrs/v3_0/rom1_ne.pdf
   creation_date: 1972
   confirmation_date: 2013

data/maps/un-ori-Orya-Latn-1972.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 1972
   language: iso-639-2:ori
   source_script: Orya
   destination_script: Latn
-  name: Romanization of Oriya (1972)
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Oriya Romanization, 1972
   url: http://www.eki.ee/wgrs/v2_2/rom1_or.pdf
   creation_date: 1972
   confirmation_date: 2003

data/maps/un-pan-Guru-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:pan
   source_script: Guru
   destination_script: Latn
-  name: Romanization of Panjabi -- UNGEGN 4.0 (1972)
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Panjabi Romanization Version 4.0
   url: https://www.eki.ee/wgrs/rom1_pa.htm
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-prs-Arab-Latn-1967.imp

@@ -5,7 +5,7 @@ metadata {
   # prs stands for Dari (https://iso639-3.sil.org/code/prs&_ga=GA1.2.2054538372.1574092823)
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Persian (1967)
+  name: Persian UN 1967
   url: http://www.eki.ee/wgrs/v2_2/rom1_fa.htm
   creation_date: 1967
   confirmation_date: 01-2003
@@ -130,20 +130,20 @@ stage {
 
     # NOTE 1
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "ot t" # الت
-    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "os̄ s̄" # الث
-    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "od d" # الد
-    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "oz̄ z̄" # الذ
-    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "or r" # الر
-    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "oz z" # الز
-    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "os s" # الس
-    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "osh sh" # الش
-    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "oş ş" # الص
-    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "oẕ ẕ" # الض
-    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "oţ ţ" # الط
-    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "oz̧ z̧" # الظ
-    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "ol l" # الل
-    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "on n" # الن
+    sub boundary + "\u0627\u0644\u062a", "ot t" # الت
+    sub boundary + "\u0627\u0644\u062b", "os̄ s̄" # الث
+    sub boundary + "\u0627\u0644\u062f", "od d" # الد
+    sub boundary + "\u0627\u0644\u0630", "oz̄ z̄" # الذ
+    sub boundary + "\u0627\u0644\u0631", "or r" # الر
+    sub boundary + "\u0627\u0644\u0632", "oz z" # الز
+    sub boundary + "\u0627\u0644\u0633", "os s" # الس
+    sub boundary + "\u0627\u0644\u0634", "osh sh" # الش
+    sub boundary + "\u0627\u0644\u0635", "oş ş" # الص
+    sub boundary + "\u0627\u0644\u0636", "oẕ ẕ" # الض
+    sub boundary + "\u0627\u0644\u0637", "oţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0638", "oz̧ z̧" # الظ
+    sub boundary + "\u0627\u0644\u0644", "ol l" # الل
+    sub boundary + "\u0627\u0644\u0646", "on n" # الن
 
     sub "\u0650\u064a\u0651", "īy" # ـِيَّ
     sub "\u0650\u064a", "iy", after: any("\u064e\u064f") # ـِي kasra followed by ي

data/maps/un-rus-Cyrl-Latn-1987.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: un
+  authority_id: ungegn
   id: 1987
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Russian (1987)
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Russian Romanization system
   url: http://www.eki.ee/wgrs/rom1_ru.htm
   creation_date: 1987
   confirmation_date: 2016

data/maps/un-sin-Sinh-Latn-1972.imp

@@ -4,8 +4,7 @@ metadata {
   language: iso-639-2:sin
   source_script: Sinh
   destination_script: Latn
-  name: Romanization of Sinhalese -- UNGEGN 4.0 (1972)
-  source: "Second United Nations Conference on the Standardization of Geographical Names. London, 10–31 May 1972. Vol. II. Technical papers, pp. 151–152."
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Sinhalese Romanization Version 4.0
   url: https://www.eki.ee/wgrs/rom1_ml.htm
   creation_date: 1972
   confirmation_date: 2016
@@ -19,6 +18,7 @@ metadata {
     Vowels and diphthongs are marked in two ways: as independent characters (used syllable-initially) and in an
     abbreviated form, to denote vowels after consonants.
 
+
   notes:
     - |
       The character ඇ was romanized as a͝i and the character ඈ as ai in Sharma's table, but there was no romanization for the character ඓ which,
@@ -37,13 +37,13 @@ metadata {
 
 tests {
   test "ශී‍්‍ර ලංකාවේ කී‍්‍රඩාව ඉතිහාසයේ ඉහළම තැනකට ගේන්න කටයුතු කරනවා", "shīra laṁkāve kīraḍāva itihāsaye ihaḷama tæ̆nakaṭa genna kaṭayutu karanavā"
-  test "කොච්චිකඬේ මෝයකට අසල නෑමට ගිය තරුණයෝ ෩ක් මරුට - මිතුරාගේ උපන් දිනය සැමරීමට ඇවිත්", "kŏchchikaṇḍae moyakaṭa asala næmaṭa giya taruṇayo 3k maruṭa - miturāge upan dinaya sæ̆marīmaṭa æ̆vit"
+  test "කොච්චිකඬේ මෝයකට අසල නෑමට ගිය තරුණයෝ ෩ක් මරුට - මිතුරාගේ උපන් දිනය සැමරීමට ඇවිත්", "kŏchchikaඬe moyakaṭa asala næmaṭa giya taruṇayo 3k maruṭa - miturāge upan dinaya sæ̆marīmaṭa æ̆vit"
   test "ලෝක ළමා දිනයදා සිසුන් පිරිසක් කසිප්පු බීලා", "loka ḷamā dinayadā sisun pirisak kasippu bīlā"
   test "කෝටි 16ක හෙරොයින් සමග දන්කොටුවේදී 7ක් දැලේ", "koṭi 16ka hĕrŏyin samaga dankŏṭuvedī 7k dæ̆le"
   test "මිනුවන්ගොඩ පීසීආර් දෙදහසක් සිදුකරයි", "minuvangŏḍa pīsīār dĕdahasak sidukarayi"
   test "පාස්කු ප‍්‍රහාරය වගේම පාස්කු ප්‍රෝඩාව ගැනත් සොයන්න කොමිසමක් පත්කළ යුතුයි - විපක්‍ෂ නායක සජිත් පේ‍්‍රමදාස", "pāsku parahāraya vagema pāsku proḍāva gæ̆nat sŏyanna kŏmisamak patkaḷa yutuyi - vipakṣha nāyaka sajit peramadāsa"
   test "ට‍්‍රම්ප්ගේ සෞඛ්‍යය තීරණාත්මකයි - ට්විටර් හරහා ජනතාව අමතයි", "ṭarampge saukhyaya tīraṇātmakayi - ṭviṭar harahā janatāva amatayi"
-  test "පාස්කු දා ප‍්‍රහාරය පිළිබඳ පරීක්‍ෂණවලින් කිසිවකුට අසාධාරණයක් වීමට ඉඩ දෙන්නේ නෑ - අගමැති", "pāsku dā parahāraya piḷibanda parīkṣhaṇavalin kisivakuṭa asādhāraṇayak vīmaṭa iḍa dĕnne næ - agamæ̆ti"
+  test "පාස්කු දා ප‍්‍රහාරය පිළිබඳ පරීක්‍ෂණවලින් කිසිවකුට අසාධාරණයක් වීමට ඉඩ දෙන්නේ නෑ - අගමැති", "pāsku dā parahāraya piḷibaඳ parīkṣhaṇavalin kisivakuṭa asādhāraṇayak vīmaṭa iḍa dĕnne næ - agamæ̆ti"
   test "දිල්ලි කැපිටල්ස් සහ කෝලිගේ බැංගලෝර් තෙවැනි ජය ලබයි", "dilli kæ̆piṭals saha kolige bæ̆ṁgalor tĕvæ̆ni jaya labayi"
   test "ශ‍්‍රී ලාංකික සම්භවයක් සහිත ප‍්‍රංශයේ පවුලක 5 ක් ඝාතනය කරලා", "sharī lāṁkika sambhavayak sahita paraṁshaye pavulaka 5 k ghātanaya karalā"
   test "පැතිකුදය ඉක්මනින් සුව කරන ප‍්‍රතිකාර", "pæ̆tikudaya ikmanin suva karana paratikāra"
@@ -171,18 +171,6 @@ stage {
     sub "ෆ", "fa"
     sub "ළ", "ḷa"
 
-    # Prenasalized sounds
-    sub "ඟ", "ṅga"
-    sub "ඦ", "ñja"
-    sub "ඬ", "ṇḍa"
-    sub "ඳ", "nda"
-    sub "ඹ", "mba"
-
-    # Other ligatures
-    sub "ක්‍ෂ", "kṣha"
-    sub "ඥ", "jña"
-    sub "න්‍ද", "nda"
-
     # numbers
     sub "\u0DE6", "0"
     sub "\u0DE7", "1"

data/maps/un-tam-Taml-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tam
   source_script: Gujr
   destination_script: Taml
-  name: Romanization of Tamil -- UNGEGN 4.0 (1972)
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Tamil Romanization Version 4.0
   url: https://www.eki.ee/wgrs/rom1_ta.htm
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-tel-Telu-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tel
   source_script: Telu
   destination_script: Latn
-  name: Romanization of Telugu -- UNGEGN 4.0 (1972)
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Telugu Romanization, 1972
   url: https://www.eki.ee/wgrs/rom1_te.htm
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-ukr-Cyrl-Latn-1998.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ukr
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Belarusian, Russian And Ukrainian Cyrillic (1998)
+  name: ROMANIZATION SYSTEM FOR BELARUSIAN, RUSSIAN AND UKRAINIAN CYRILLIC
   url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/7th-uncsgn-docs/econf/7th_UNCSGN_econf.91_3_Add1.pdf
   # page 320
   creation_date: 1998

data/maps/un-ukr-Cyrl-Latn-2012.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ukr
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Belarusian, Russian And Ukrainian Cyrillic (2012)
+  name: ROMANIZATION SYSTEM FOR BELARUSIAN, RUSSIAN AND UKRAINIAN CYRILLIC
   url: http://www.eki.ee/wgrs/rom1_uk.htm
   creation_date: 2010
 }