Index: source/data/translit/am_am_Latn_BGN.txt |
diff --git a/source/data/translit/Amharic_Latin_BGN.txt b/source/data/translit/am_am_Latn_BGN.txt |
similarity index 69% |
rename from source/data/translit/Amharic_Latin_BGN.txt |
rename to source/data/translit/am_am_Latn_BGN.txt |
index 44d68056b1079c2ad47975bf1fcf5769034ba4d6..76e05791063d8a2d75fb9e6f215fb3ceec3ca350 100644 |
--- a/source/data/translit/Amharic_Latin_BGN.txt |
+++ b/source/data/translit/am_am_Latn_BGN.txt |
@@ -1,18 +1,36 @@ |
-# *************************************************************************** |
-# * |
-# * Copyright (C) 2004-2015, International Business Machines |
-# * Corporation; Unicode, Inc.; and others. All Rights Reserved. |
-# * |
-# *************************************************************************** |
-# File: Amharic_Latin_BGN.txt |
-# Generated from CLDR |
+# © 2016 and later: Unicode, Inc. and others. |
+# License & terms of use: http://www.unicode.org/copyright.html#License |
# |
+# File: am_am_Latn_BGN.txt |
+# Generated from CLDR |
+# |
+ |
+######################################################################## |
+# BGN/PCGN 1967 System |
+# |
+# The BGN/PCGN system for Amharic was designed for use in romanizing |
+# names written in Amharic characters. The Roman letters and letter |
+# combinations shown as equivalents to the Amharic characters reflect |
+# modern Amharic pronunciation. Different consonant characters in three |
+# groups are pronounced alike in modern Amharic and are therefore |
+# romanized identically for use in geographic names. |
+# |
+# https://www.gov.uk/government/uploads/system/uploads/attachment_data/file/320088/Amharic_Romanization.pdf |
+# |
+# Originally prepared by Michael Everson <everson@evertype.com> |
+######################################################################## |
+# MINIMAL FILTER: Amharic-Latin |
:: [ሀ-᎙] ; |
:: NFD (NFC) ; |
$ejective = ’; |
$glottal = ’; |
$pharyngeal = ‘; |
+# Use this $wordBoundary until bug 2034 is fixed in ICU: |
+# http://bugs.icu-project.org/trac/ticket/2034 |
$wordBoundary = [^[:L:][:M:][:N:]] ; |
+######################################################################## |
+# Start of Syllabic Transformations |
+######################################################################## |
ሀ → hā ; # ETHIOPIC SYLLABLE HA |
ሁ → hu ; # ETHIOPIC SYLLABLE HU |
ሂ → hī ; # ETHIOPIC SYLLABLE HI |
@@ -28,6 +46,12 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ል → li ; # ETHIOPIC SYLLABLE LE |
ሎ → lo ; # ETHIOPIC SYLLABLE LO |
ሏ → lwa ; # ETHIOPIC SYLLABLE LWA |
+######################################################################## |
+# BGN Page 3 Rule 2: |
+# |
+# For documentation purposes the characters romanized with h in rows |
+# 1, 3, 13 and 18 may be romanized with h, h\u0323, h\u032E, and h\u0331, respectively. |
+######################################################################## |
ሐ → h\u0323ā ; # ETHIOPIC SYLLABLE HHA |
ሑ → h\u0323u ; # ETHIOPIC SYLLABLE HHU |
ሒ → h\u0323ī ; # ETHIOPIC SYLLABLE HHI |
@@ -35,6 +59,9 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ሔ → h\u0323ē ; # ETHIOPIC SYLLABLE HHEE |
ሕ → h\u0323i ; # ETHIOPIC SYLLABLE HHE |
ሖ → h\u0323o ; # ETHIOPIC SYLLABLE HHO |
+######################################################################## |
+# End of Rule 2 |
+######################################################################## |
መ → me ; # ETHIOPIC SYLLABLE MA |
ሙ → mu ; # ETHIOPIC SYLLABLE MU |
ሚ → mī ; # ETHIOPIC SYLLABLE MI |
@@ -43,6 +70,14 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ም → mi ; # ETHIOPIC SYLLABLE ME |
ሞ → mo ; # ETHIOPIC SYLLABLE MO |
ሟ → mwa ; # ETHIOPIC SYLLABLE MWA |
+######################################################################## |
+# BGN Page 3 Rule 2: |
+# |
+# The characters romanized with s in rows 5 and 7 may, instead, be |
+# romanized with š and s, respectively; and the characters romanized |
+# with ts’ in rows 30 and 31 may, instead, be romanized with ts’ and |
+# t\u035Fs’ respectively. |
+######################################################################## |
ሠ → še ; # ETHIOPIC SYLLABLE SZA |
ሡ → šu ; # ETHIOPIC SYLLABLE SZU |
ሢ → šī ; # ETHIOPIC SYLLABLE SZI |
@@ -50,6 +85,9 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ሤ → šē ; # ETHIOPIC SYLLABLE SZEE |
ሥ → ši ; # ETHIOPIC SYLLABLE SZE |
ሦ → šo ; # ETHIOPIC SYLLABLE SZO |
+######################################################################## |
+# End of Rule 2 |
+######################################################################## |
ረ → re ; # ETHIOPIC SYLLABLE RA |
ሩ → ru ; # ETHIOPIC SYLLABLE RU |
ሪ → rī ; # ETHIOPIC SYLLABLE RI |
@@ -81,11 +119,20 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ቄ → k $ejective ē ; # ETHIOPIC SYLLABLE QEE |
ቅ → k $ejective i ; # ETHIOPIC SYLLABLE QE |
ቆ → k $ejective o ; # ETHIOPIC SYLLABLE QO |
+# |
+# No rule yet for ቇ U+1247 ETHIOPIC SYLLABLE QOA |
ቈ → k $ejective o ; # ETHIOPIC SYLLABLE QWA |
ቍ → k $ejective wi ; # ETHIOPIC SYLLABLE QWE |
ቋ → k $ejective wa ; # ETHIOPIC SYLLABLE QWAA |
ቌ → k $ejective wē ; # ETHIOPIC SYLLABLE QWEE |
ቊ → k $ejective wī ; # ETHIOPIC SYLLABLE QWI |
+######################################################################## |
+# BGN Page 3 Rule 3: |
+# |
+# The character ቐ which occurs only in the writing system of the Tigre |
+# and # Tigrinya languages, should be romanized with k’ in geographic |
+# names but may be romanized with k\u0331 in documentation. |
+######################################################################## |
ቐ → k\u0331 $ejective e ; # ETHIOPIC SYLLABLE QHA |
ቑ → k\u0331 $ejective u ; # ETHIOPIC SYLLABLE QHU |
ቒ → k\u0331 $ejective ī ; # ETHIOPIC SYLLABLE QHI |
@@ -98,6 +145,9 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ቛ → k\u0331 $ejective wa ; # ETHIOPIC SYLLABLE QHWAA |
ቜ → k\u0331 $ejective wē ; # ETHIOPIC SYLLABLE QHWEE |
ቝ → k\u0331 $ejective wi ; # ETHIOPIC SYLLABLE QHWE |
+######################################################################## |
+# End of Rule 3 |
+######################################################################## |
በ → be ; # ETHIOPIC SYLLABLE BA |
ቡ → bu ; # ETHIOPIC SYLLABLE BU |
ቢ → bī ; # ETHIOPIC SYLLABLE BI |
@@ -122,6 +172,12 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ች → chi ; # ETHIOPIC SYLLABLE CE |
ቾ → cho ; # ETHIOPIC SYLLABLE CO |
ቿ → chwa ; # ETHIOPIC SYLLABLE CWA |
+######################################################################## |
+# BGN Page 3 Rule 2: |
+# |
+# For documentation purposes the characters romanized with h in rows |
+# 1, 3, 13 and 18 may be romanized with h, h\u0323, h\u032E, and h\u0331, respectively. |
+######################################################################## |
ኀ → h\u032Eā ; # ETHIOPIC SYLLABLE XA |
ኁ → h\u032Eu ; # ETHIOPIC SYLLABLE XU |
ኂ → h\u032Eī ; # ETHIOPIC SYLLABLE XI |
@@ -129,11 +185,15 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ኄ → h\u032Eē ; # ETHIOPIC SYLLABLE XEE |
ኅ → h\u032Ei ; # ETHIOPIC SYLLABLE XE |
ኆ → h\u032Eo ; # ETHIOPIC SYLLABLE XO |
+# No rule yet for ኇ U+1287 ETHIOPIC SYLLABLE XOA |
ኈ → h\u032Eo; # ETHIOPIC SYLLABLE XWA |
ኊ → h\u032Ewī ; # ETHIOPIC SYLLABLE XWI |
ኋ → h\u032Ewa ; # ETHIOPIC SYLLABLE XWAA |
ኌ → h\u032Ewē ; # ETHIOPIC SYLLABLE XWEE |
ኍ → h\u032Ewi ; # ETHIOPIC SYLLABLE XWE |
+######################################################################## |
+# End of Rule 2 |
+######################################################################## |
ነ → ne ; # ETHIOPIC SYLLABLE NA |
ኑ → nu ; # ETHIOPIC SYLLABLE NU |
ኒ → nī ; # ETHIOPIC SYLLABLE NI |
@@ -150,6 +210,13 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ኝ → nyi ; # ETHIOPIC SYLLABLE NYE |
ኞ → nyo ; # ETHIOPIC SYLLABLE NYO |
ኟ → nywa ; # ETHIOPIC SYLLABLE NYWA |
+######################################################################## |
+# BGN Page 3 Rule 5: |
+# |
+# The vowel characters in row 16 should be Romanized ā, u, ī, a, ē, i, |
+# and o initially and ’ā, ’u, ’ī, ’a, ’ē, ’i, and ’o in all other |
+# positions. |
+######################################################################## |
$wordBoundary{አ → ā ; # ETHIOPIC SYLLABLE GLOTTAL A |
$wordBoundary{ኡ → u ; # ETHIOPIC SYLLABLE GLOTTAL U |
$wordBoundary{ኢ → ī ; # ETHIOPIC SYLLABLE GLOTTAL I |
@@ -166,6 +233,9 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
እ → $glottal i ; # ETHIOPIC SYLLABLE GLOTTAL E |
ኦ → $glottal o ; # ETHIOPIC SYLLABLE GLOTTAL O |
ኧ → $glottal e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
+######################################################################## |
+# End of Rule 5 |
+######################################################################## |
ከ → ke ; # ETHIOPIC SYLLABLE KA |
ኩ → ku ; # ETHIOPIC SYLLABLE KU |
ኪ → kī ; # ETHIOPIC SYLLABLE KI |
@@ -173,11 +243,18 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ኬ → kē ; # ETHIOPIC SYLLABLE KEE |
ክ → ki ; # ETHIOPIC SYLLABLE KE |
ኮ → ko ; # ETHIOPIC SYLLABLE KO |
+# No rule yet for ኯ U+12AF ETHIOPIC SYLLABLE KOA |
ኰ → ko ; # ETHIOPIC SYLLABLE KWA |
ኲ → kwī ; # ETHIOPIC SYLLABLE KWI |
ኳ → kwa ; # ETHIOPIC SYLLABLE KWAA |
ኴ → kwē ; # ETHIOPIC SYLLABLE KWEE |
ኵ → kwi ; # ETHIOPIC SYLLABLE KWE |
+######################################################################## |
+# BGN Page 3 Rule 2: |
+# |
+# For documentation purposes the characters romanized with h in rows |
+# 1, 3, 13 and 18 may be romanized with h, h\u0323, h\u032E, and h\u0331, respectively. |
+######################################################################## |
ኸ → h\u0331e ; # ETHIOPIC SYLLABLE KXA |
ኹ → h\u0331u ; # ETHIOPIC SYLLABLE KXU |
ኺ → h\u0331ī ; # ETHIOPIC SYLLABLE KXI |
@@ -185,6 +262,14 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ኼ → h\u0331ē ; # ETHIOPIC SYLLABLE KXEE |
ኽ → h\u0331i ; # ETHIOPIC SYLLABLE KXE |
ኾ → h\u0331o ; # ETHIOPIC SYLLABLE KXO |
+# No rule yet for ዀ U+12C0 ETHIOPIC SYLLABLE KXWA |
+# No rule yet for ዂ U+12C2 ETHIOPIC SYLLABLE KXWI |
+# No rule yet for ዃ U+12C3 ETHIOPIC SYLLABLE KXWAA |
+# No rule yet for ዄ U+12C4 ETHIOPIC SYLLABLE KXWEE |
+# No rule yet for ዅ U+12C5 ETHIOPIC SYLLABLE KXWE |
+######################################################################## |
+# End of Rule 2 |
+######################################################################## |
ወ → we ; # ETHIOPIC SYLLABLE WA |
ዉ → wu ; # ETHIOPIC SYLLABLE WU |
ዊ → wī ; # ETHIOPIC SYLLABLE WI |
@@ -192,6 +277,7 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ዌ → wē ; # ETHIOPIC SYLLABLE WEE |
ው → wi ; # ETHIOPIC SYLLABLE WE |
ዎ → wo ; # ETHIOPIC SYLLABLE WO |
+# No rule yet for ዏ U+12CF ETHIOPIC SYLLABLE WOA |
ዐ → $pharyngeal ā ; # ETHIOPIC SYLLABLE PHARYNGEAL A |
ዑ → $pharyngeal u ; # ETHIOPIC SYLLABLE PHARYNGEAL U |
ዒ → $pharyngeal ī ; # ETHIOPIC SYLLABLE PHARYNGEAL I |
@@ -230,6 +316,7 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ድ → di ; # ETHIOPIC SYLLABLE DE |
ዶ → do ; # ETHIOPIC SYLLABLE DO |
ዷ → dwa ; # ETHIOPIC SYLLABLE DWA |
+# No rule yet for ዸ U+12F8 ETHIOPIC SYLLABLE DDA ... |
ጀ → je ; # ETHIOPIC SYLLABLE JA |
ጁ → ju ; # ETHIOPIC SYLLABLE JU |
ጂ → jī ; # ETHIOPIC SYLLABLE JI |
@@ -245,11 +332,15 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ጌ → gē ; # ETHIOPIC SYLLABLE GEE |
ግ → gi ; # ETHIOPIC SYLLABLE GE |
ጎ → go ; # ETHIOPIC SYLLABLE GO |
+# No rule yet for ጏ U+130F ETHIOPIC SYLLABLE GOA |
ጐ → go ; # ETHIOPIC SYLLABLE GWA |
ጒ → gwī ; # ETHIOPIC SYLLABLE GWI |
ጓ → gwa ; # ETHIOPIC SYLLABLE GWAA |
ጔ → gwē ; # ETHIOPIC SYLLABLE GWEE |
ጕ → gwi ; # ETHIOPIC SYLLABLE GWE |
+# No rule yet for ጘ U+1318 ETHIOPIC SYLLABLE GGA |
+# ...ጙጚጛጜጝጞ... |
+# No rule yet for ጟ U+131F ETHIOPIC SYLLABLE GGWAA |
ጠ → t $ejective e ; # ETHIOPIC SYLLABLE THA |
ጡ → t $ejective u ; # ETHIOPIC SYLLABLE THU |
ጢ → t $ejective ī ; # ETHIOPIC SYLLABLE THI |
@@ -274,6 +365,14 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ጵ → p $ejective i ; # ETHIOPIC SYLLABLE PHE |
ጶ → p $ejective o ; # ETHIOPIC SYLLABLE PHO |
ጷ → p $ejective wa ; # ETHIOPIC SYLLABLE PHWA |
+######################################################################## |
+# BGN Page 3 Rule 2: |
+# |
+# The characters romanized with s in rows 5 and 7 may, instead, be |
+# romanized with š and s, respectively; and the characters romanized |
+# with ts’ in rows 30 and 31 may, instead, be romanized with ts’ and |
+# t\u035Fs’ respectively. |
+######################################################################## |
ጸ → ts $ejective e ; # ETHIOPIC SYLLABLE TSA |
ጹ → ts $ejective u ; # ETHIOPIC SYLLABLE TSU |
ጺ → ts $ejective ī ; # ETHIOPIC SYLLABLE TSI |
@@ -289,6 +388,10 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ፄ → t\u035Fs $ejective ē ; # ETHIOPIC SYLLABLE TZEE |
ፅ → t\u035Fs $ejective i ; # ETHIOPIC SYLLABLE TZE |
ፆ → t\u035Fs $ejective o ; # ETHIOPIC SYLLABLE TZO |
+# No rule yet for ፇ U+1347 ETHIOPIC SYLLABLE TZOA |
+######################################################################## |
+# End of Rule 2 |
+######################################################################## |
ፈ → fe ; # ETHIOPIC SYLLABLE FA |
ፉ → fu ; # ETHIOPIC SYLLABLE FU |
ፊ → fī ; # ETHIOPIC SYLLABLE FI |
@@ -308,6 +411,7 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ፘ → rya ; # ETHIOPIC SYLLABLE RYA |
ፙ → mya ; # ETHIOPIC SYLLABLE MYA |
ፚ → fya ; # ETHIOPIC SYLLABLE FYA |
+# No rule yet for ፚ U+135A ETHIOPIC SYLLABLE FYA |
ቨ → ve ; # ETHIOPIC SYLLABLE VA |
ቩ → vu ; # ETHIOPIC SYLLABLE VU |
ቪ → vī ; # ETHIOPIC SYLLABLE VI |
@@ -316,6 +420,11 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
ቭ → vi ; # ETHIOPIC SYLLABLE VE |
ቮ → vo ; # ETHIOPIC SYLLABLE VO |
ቯ → vwa ; # ETHIOPIC SYLLABLE VWA |
+######################################################################## |
+# Start of Numeric Transformations |
+# |
+# The BGN table on page 3 does not include ፼. |
+######################################################################## |
፩ → 1 ; # ETHIOPIC DIGIT ONE |
፪ → 2 ; # ETHIOPIC DIGIT TWO |
፫ → 3 ; # ETHIOPIC DIGIT THREE |
@@ -335,3 +444,4 @@ $wordBoundary{ኧ → e ; # ETHIOPIC SYLLABLE GLOTTAL WA |
፹ → 80 ; # ETHIOPIC NUMBER EIGHTY |
፺ → 90 ; # ETHIOPIC NUMBER NINETY |
፻ → 100 ; # ETHIOPIC NUMBER HUNDRED |
+ |