diff options
Diffstat (limited to 'intl/icu/source/data/translit/am_am_FONIPA.txt')
| -rw-r--r-- | intl/icu/source/data/translit/am_am_FONIPA.txt | 701 |
1 files changed, 701 insertions, 0 deletions
diff --git a/intl/icu/source/data/translit/am_am_FONIPA.txt b/intl/icu/source/data/translit/am_am_FONIPA.txt new file mode 100644 index 0000000000..480ed56a8d --- /dev/null +++ b/intl/icu/source/data/translit/am_am_FONIPA.txt @@ -0,0 +1,701 @@ +# © 2016 and later: Unicode, Inc. and others. +# License & terms of use: http://www.unicode.org/copyright.html +# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml +# +# File: am_am_FONIPA.txt +# Generated from CLDR +# + +# Transforms Amharic (am) to Amharic in phonemic IPA transcription (am_FONIPA). +# +# Long vowels, long/geminated consonants: +# In the direction from am_FONIPA to am, we emit Ethiopic gemination +# and vowel length markers (U+135D, U+135E, U+135F) although +# they are rarely written in Amharic text. Exceptions include +# school books and textbooks for non-native speakers. +# Clients who do not want these markers can easily strip them off +# in a post-processing step. +# +# Labialization: +# Amharic speakers will usually say ሟ as [mʷa] instead of [mwa]; +# labializing [m] instead of saying [m] followed by a separate [w]. +# Most Amharic consonants can get labialized. To keep the phonemic +# transcription simple, we emit /m/ + /w/; otherwise, our phoneme +# set would almost double, and it would include very unusual phonemes +# such as /ɲʷ/ or /t\u0361ʃʼʷ/. +# +# References: +# [1] The Ge’ez Frontier Foundation: “Principles and Specification +# for Mnemonic Ethiopic Keyboards.” Version of January 17, 2009; +# retrieved on November 4, 2014. +# http://keyboards.ethiopic.org/specification/GFF-MnemonicEthiopicKeyboardSpecification.pdf +# Other than most online sources, this report uses correct IPA notation +# with the exception of /j/, which it consistently (but wrongly) +# writes as */y/. +$IPA_VOWEL = [aeəiɨou]; +$IPA_CONSONANT = [mnɲɴ p{pʼ}bt{tʼ}dk{kʼ}ɡʔʕ fvs{sʼ}zʃʒxh lr {t\u0361ʃ}{t\u0361ʃʼ}{d\u0361ʒ}]; +# Some consonants have a special syllable when labialized, such as ፗ ↔ /pʷa/. +# Amharic restricts this mostly to /a/ syllables. While the Ethiopic script +# does offer labialized syllables for other vowels, these are typically +# not written in Amharic. +$LABIALIZABLE_BEFORE_A = [p{pʼ}t{tʼ} {t\u0361ʃ}{t\u0361ʃʼ}{d\u0361ʒ}{d\u0361ʒʼ} s{sʼ}zʃʒ fv r]; +← [ ʼ \u0361 \u035C \u032F]; +::(null); +# Appendix B of [1] transcribes ሀ as /hə/. However, according to +# an Amharic-speaking person, there is no /hə/ sequence +# in Amharic; instead, it gets pronounced as /ha/. +ሀ → ha; +ሀ ← hə; +ሁ ↔ hu; +ሂ ↔ hi; +ሃ ↔ ha; +ሄ ↔ he; +ህ ↔ hɨ; +ሆ ↔ ho; +ሇ → ho; # Dizi, Me’en, Mursi, Suri /hɔ/ ([1], Appendix E); not used in Amharic. +ህ ← h; +ለ ↔ lə; +ሉ ↔ lu; +ሊ ↔ li; +ላ ↔ la; +ሌ ↔ le; +ል ↔ lɨ; +ሎ ↔ lo; +ⶀ → lo; # Dizi, Me’en, Mursi, Suri /lɔ/ ([1], Appendix E); not used in Amharic. +ሏ ↔ lwa; +ል ← l; +# Appendix B of [1] transcribes ሐ as Voiceless pharyngeal fricative +# /ħə/. However, according to an Amharic-speaking person, Amharic +# makes no difference in pronunciation between ሐ...ሓ and ሀ...ሃ; both +# are pronounced as Voiceless glottal fricative /h/. Also, according +# to the speaker there is no /hə/ sequence in Amharic; instead, it +# gets pronounced as /ha/. +ሐ → ha; +ሑ → hu; +ሒ → hi; +ሓ → ha; +ሔ → he; +ሕ → hɨ; +ሖ → ho; +ሗ → hwa; +መ ↔ mə; +ሙ ↔ mu; +ሚ ↔ mi; +ማ ↔ ma; +ሜ ↔ me; +ም ↔ mɨ; +ሞ ↔ mo; +ⶁ → mo; # Dizi, Me’en, Mursi, Suri /mɔ/ ([1], Appendix E); not used in Amharic. +ᎀ → mwə; # Sebatbeit /mwə/ ([1], Appendix H); not used in Amharic. +ᎃ → mwu; # Sebatbeit /mwu/ ([1], Appendix H); not used in Amharic. +ᎁ → mwi; # Sebatbeit /mwi/ ([1], Appendix H); not used in Amharic. +ሟ ↔ mwa; +ᎂ → mwe; # Sebatbeit /mwe/ ([1], Appendix H); not used in Amharic. +ፙ → mja; # Unclear which language; Appendix L of [1] transcribes ፙ as /mʲa/. +ም ← m; +ሠ → sə; +ሡ → su; +ሢ → si; +ሣ → sa; +ሤ → se; +ሥ → sɨ; +ሦ → so; +ሧ → swa; +ረ ↔ rə; +ሩ ↔ ru; +ሪ ↔ ri; +ራ ↔ ra; +ሬ ↔ re; +ር ↔ rɨ; +ሮ ↔ ro; +ⶂ → ro; # Dizi, Me’en, Mursi, Suri /rɔ/ ([1], Appendix E); not used in Amharic. +ሯ ↔ rwa; +ፘ → rja; # Unclear which language; Appendix L of [1] transcribes ፘ as /rʲa/. +ር ← r; +# Amharic speakers pronounce ⶠ like ሸ. Source: [1], Appendix B. +ⶠ → ʃə; +ⶡ → ʃu; +ⶢ → ʃi; +ⶣ → ʃa; +ⶤ → ʃe; +ⶥ → ʃɨ; +ⶦ → ʃo; +ሸ ↔ ʃə; +ሹ ↔ ʃu; +ሺ ↔ ʃi; +ሻ ↔ ʃa; +ሼ ↔ ʃe; +ሽ ↔ ʃɨ; +ሾ ↔ ʃo; +ⶄ → ʃo; # Dizi, Me’en, Mursi, Suri /ʃɔ/ ([1], Appendix E); not used in Amharic. +ሿ ↔ ʃwa; +ሽ ← ʃ; +ቀ ↔ kʼə; +ቁ ↔ kʼu; +ቂ ↔ kʼi; +ቃ ↔ kʼa; +ቄ ↔ kʼe; +ቅ ↔ kʼɨ; +ቆ ↔ kʼo; +ቇ → kʼo; # Dizi, Me’en, Mursi, Suri /kʼɔ/ ([1], Appendix E); not used in Amharic. +ቈ ↔ kʼwə; +ቍ ↔ kʼwu; +ቊ ↔ kʼwi; +ቋ ↔ kʼwa; +ቌ ↔ kʼwe; +ቅ ← kʼ; +# In Awngi, Blin, Qimant, and Xamtanga, ቐ is spoken as voiced uvular fricative [ʁ]. +# Source: [1], Appendix C. However, */ʁ/ is not an Amharic phoneme. +# When reading foreign words with ቐ, Amharic speakers pronounce +# ቐ like ቀ, i.e. as velar ejective /kʼ/. +ቐ → kʼə; +ቑ → kʼu; +ቒ → kʼi; +ቓ → kʼa; +ቔ → kʼe; +ቕ → kʼɨ; +ቖ → kʼo; +ቘ → kʼwə; +ቝ → kʼwu; +ቚ → kʼwi; +ቛ → kʼwa; +ቜ → kʼwe; +# In Sebatbeit, ⷀ is spoken as palatalized velar ejective /kʼʲ/ ([1], Appendix H). +# In Amharic, the syllable is not used, but it might appear in names. +ⷀ → kʼjə; +ⷁ → kʼju; +ⷂ → kʼji; +ⷃ → kʼja; +ⷄ → kʼje; +ⷅ → kʼjɨ; +ⷆ → kʼjo; +በ ↔ bə; +ቡ ↔ bu; +ቢ ↔ bi; +ባ ↔ ba; +ቤ ↔ be; +ብ ↔ bɨ; +ቦ ↔ bo; +ⶅ → bo; # Dizi, Me’en, Mursi, Suri /bɔ/ ([1], Appendix E); not used in Amharic. +ᎄ → bwə; # Sebatbeit /bʷə/ ([1], Appendix H); not used in Amharic. +ᎇ → bwu; # Sebatbeit /bʷu/ ([1], Appendix H); not used in Amharic. +ᎅ → bwi; # Sebatbeit /bʷi/ ([1], Appendix H); not used in Amharic. +ቧ → bwa; # Sebatbeit /bʷa/ ([1], Appendix H); not used in Amharic. +ᎆ → bwe; # Sebatbeit /bʷe/ ([1], Appendix H); not used in Amharic. +ብ ← b; +ቨ ↔ və; +ቩ ↔ vu; +ቪ ↔ vi; +ቫ ↔ va; +ቬ ↔ ve; +ቭ ↔ vɨ; +ቮ ↔ vo; +ቯ ↔ vwa; +ቭ ← v; +# Unclear which Ethiopic language uses ⶨ. It only appears in the +# “Language Neutral” list of Appendix L in [1], which transcribes it as t\u0361ʃ. +# For Amharic, we pronounce ⶨ therefore like ቸ. +ⶨ → t\u0361ʃə; +ⶩ → t\u0361ʃu; +ⶪ → t\u0361ʃi; +ⶫ → t\u0361ʃa; +ⶬ → t\u0361ʃe; +ⶭ → t\u0361ʃɨ; +ⶮ → t\u0361ʃo; +# In Amharic, ኀ is pronounced like ሀ. +# Source: [1], section on “Phonological Redundancy” for Amharic, page 5. +# Appendix B of [1] transcribes ሀ as /hə/. However, according to +# an Amharic-speaking person, there is no /hə/ sequence in Amharic. +# Instead, ሀ (and hence also ኀ) gets pronounced as /ha/. +ኀ → ha; +ኁ → hu; +ኂ → hi; +ኃ → ha; +ኄ → he; +ኅ → hɨ; +ኆ → ho; +ኇ → ho; # Dizi, Me’en, Mursi, Suri /ŋɔ/ ([1], Appendix E); not used in Amharic. +ኈ → hwə; +ኍ → hwu; +ኊ → hwi; +ኋ → hwa; +ኌ → hwe; +ነ ↔ nə; +ኑ ↔ nu; +ኒ ↔ ni; +ና ↔ na; +ኔ ↔ ne; +ን ↔ nɨ; +ኖ ↔ no; +ⶈ → no; # Dizi, Me’en, Mursi, Suri /nɔ/ ([1], Appendix E); not used in Amharic. +ኗ ↔ nwa; +ን ← n; +ኘ ↔ ɲə; +ኙ ↔ ɲu; +ኚ ↔ ɲi; +ኛ ↔ ɲa; +ኜ ↔ ɲe; +ኝ ↔ ɲɨ; +ኞ ↔ ɲo; +ⶉ → ɲo; # Dizi, Me’en, Mursi, Suri /ɲɔ/ ([1], Appendix E); not used in Amharic. +ኟ ↔ ɲwa; +ኝ ← ɲ; +# Amharic speakers pronounce ኸ as [h] because Amharic has no [x] sound. +# However, in transliterations of foreign (eg. Spanish) words with [x], +# several Amharic speakers have confirmed that they prefer ኻ over ሃ. +ዀ → hwə; +ዂ → hwi; +ዃ → hwa; +ዄ → hwe; +ዅ → hwɨ; +ኸ → hə; +ኹ → hu; +ኺ → hi; +ኻ → ha; +ኼ → he; +ኽ → hɨ; +ኾ → ho; +ዀ ← xwə; +ዂ ← xwi; +ዃ ← xwa; +ዄ ← xwe; +ዅ ← xwɨ; +ዅ ← xw; +ኸ ← xə; +ኹ ← xu; +ኺ ← xi; +ኻ ← xa; +ኼ ← xe; +ኽ ← xɨ; +ኾ ← xo; +ኽ ← x; +አ ↔ ʔə; +ኡ ↔ ʔu; +ኢ ↔ ʔi; +ኣ ↔ ʔa; +ኤ ↔ ʔe; +እ ↔ ʔɨ; +ኦ ↔ ʔo; +ⶊ → ʔo; # Dizi, Me’en, Mursi, Suri /ɲɔ/ ([1], Appendix E); not used in Amharic. +እ ← ʔ; +ከ ↔ kə; +ኩ ↔ ku; +ኪ ↔ ki; +ካ ↔ ka; +ኬ ↔ ke; +ክ ↔ kɨ; +ኮ ↔ ko; +ኰ ↔ kwə; +ኵ ↔ kwu; +ኲ ↔ kwi; +ኳ ↔ kwa; +ኴ ↔ kwe; +ክ ← k; +# In Sebatbeit, ⷈ is spoken as palatalized velar plosive /kʲ/ ([1], Appendix H). +# Amharic speakers pronounce it as /k/ without palatalization. +ⷈ → kə; +ⷉ → ku; +ⷊ → ki; +ⷋ → ka; +ⷌ → ke; +ⷍ → kɨ; +ⷎ → ko; +# In Sebatbeit, ⷐ is spoken as palatalized voiceless velar fricative/xʲə/ +# according to [1], Appendix H. When the syllable appears in names, +# Amharic speakers pronounce it as /kə/ without palatalization. +ⷐ → kə; +ⷑ → ku; +ⷒ → ki; +ⷓ → ka; +ⷔ → ke; +ⷕ → kɨ; +ⷖ → ko; +ወ ↔ wə; +ዉ ↔ wu; +ዊ ↔ wi; +ዋ ↔ wa; +ዌ ↔ we; +ው ↔ wɨ; +ዎ ↔ wo; +ዏ → wo; # Dizi, Me’en, Mursi, Suri /wɔ/ ([1], Appendix E); not used in Amharic. +ው ← w; +ዐ ↔ ʕə; +ዑ ↔ ʕu; +ዒ ↔ ʕi; +ዓ ↔ ʕa; +ዔ ↔ ʕe; +ዕ ↔ ʕɨ; +ዖ ↔ ʕo; +ዒ ← ʕ; +ዘ ↔ zə; +ዙ ↔ zu; +ዚ ↔ zi; +ዛ ↔ za; +ዜ ↔ ze; +ዝ ↔ zɨ; +ዞ ↔ zo; +ⶋ → zo; # Dizi, Me’en, Mursi, Suri /zɔ/ ([1], Appendix E); not used in Amharic. +ዟ ↔ zwa; +ዝ ← z; +ዠ ↔ ʒə; +ዡ ↔ ʒu; +ዢ ↔ ʒi; +ዣ ↔ ʒa; +ዤ ↔ ʒe; +ዥ ↔ ʒɨ; +ዦ ↔ ʒo; +ዧ ↔ ʒwa; +ዢ ← ʒ; +# Unclear which Ethiopic language uses ⶰ. It only appears in the +# “Language Neutral” list of Appendix L in [1], which transcribes it as ʒ. +# For Amharic, we pronounce ⶰ therefore like ዠ. +ⶰ → ʒə; +ⶱ → ʒu; +ⶲ → ʒi; +ⶳ → ʒa; +ⶴ → ʒe; +ⶵ → ʒɨ; +ⶶ → ʒo; +የ ↔ jə; +ዩ ↔ ju; +ዪ ↔ ji; +ያ ↔ ja; +ዬ ↔ je; +ይ ↔ jɨ; +ዮ ↔ jo; +ዯ → jo; # Dizi, Me’en, Mursi, Suri /zɔ/ ([1], Appendix E); not used in Amharic. +ይ ← j; +ጀ ↔ d\u0361ʒə; +ጁ ↔ d\u0361ʒu; +ጂ ↔ d\u0361ʒi; +ጃ ↔ d\u0361ʒa; +ጄ ↔ d\u0361ʒe; +ጅ ↔ d\u0361ʒɨ; +ጆ ↔ d\u0361ʒo; +ጇ ↔ d\u0361ʒwa; +ጅ ← d\u0361ʒ; +ደ ↔ də; +ዱ ↔ du; +ዲ ↔ di; +ዳ ↔ da; +ዴ ↔ de; +ድ ↔ dɨ; +ዶ ↔ do; +ⶌ → do; # Dizi, Me’en, Mursi, Suri /zɔ/ ([1], Appendix E); not used in Amharic. +ዷ ↔ dwa; +ድ ← d; +ገ ↔ ɡə; +ጉ ↔ ɡu; +ጊ ↔ ɡi; +ጋ ↔ ɡa; +ጌ ↔ ɡe; +ግ ↔ ɡɨ; +ጎ ↔ ɡo; +ጐ ↔ ɡwə; +ጕ ↔ ɡwu; +ጒ ↔ ɡwi; +ጓ ↔ ɡwa; +ጔ ↔ ɡwe; +ግ ← ɡ; +# In Awngi, Blin, Qimant, and Xamtanga, ጘ is spoken as voiced velar nasal [ŋ]. +# Source: [1], Appendix C. While /ŋ/ is not an Amharic phoneme, Amharic speakers +# still can pronounce it according to our source. However, when transliterating +# foreign words with [ŋ], Amharic uses the sequence ንግ /nɡ/. For example, +# the Amharic transliteration of Washington /waʃiŋtən/ is ዋሺንግተን. +ጘ → ŋə; +ጙ → ŋu; +ጚ → ŋi; +ጛ → ŋa; +ጜ → ŋe; +ጝ → ŋɨ; +ጞ → ŋo; +ⶓ → ŋwə; +ⶖ → ŋwu; +ⶔ → ŋwi; +ጟ → ŋwa; +ⶕ → ŋwe; +# Since there is no uvular nasal [ɴ] in Amharic, we use the velar nasal [ŋ]. +ጘ ← ɴə; +ጙ ← ɴu; +ጚ ← ɴi; +ጛ ← ɴa; +ጜ ← ɴe; +ጝ ← ɴɨ; +ጞ ← ɴo; +ጝ ← ɴ; +# In Sebatbeit, ⷘ is spoken as palatalized voiced velar stop /ɡj/ ([1], Appendix H). +# Amharic speakers pronounce it as voiced velar stop /ɡ/ without palatalization. +ⷘ → ɡə; +ⷙ → ɡu; +ⷚ → ɡi; +ⷛ → ɡa; +ⷜ → ɡe; +ⷝ → ɡɨ; +ⷞ → ɡo; +ጠ ↔ tʼə; +ጡ ↔ tʼu; +ጢ ↔ tʼi; +ጣ ↔ tʼa; +ጤ ↔ tʼe; +ጥ ↔ tʼɨ; +ጦ ↔ tʼo; +ጧ ↔ tʼwa; +ጢ ← tʼ; +ጨ ↔ t\u0361ʃʼə; +ጩ ↔ t\u0361ʃʼu; +ጪ ↔ t\u0361ʃʼi; +ጫ ↔ t\u0361ʃʼa; +ጬ ↔ t\u0361ʃʼe; +ጭ ↔ t\u0361ʃʼɨ; +ጮ ↔ t\u0361ʃʼo; +ⶐ → t\u0361ʃʼo; # Dizi, Me’en, Mursi, Suri /t\u0361ʃʼɔ/ ([1], Appendix E); not used in Amharic. +ጯ ↔ t\u0361ʃʼwa; +ጪ ← t\u0361ʃʼ; +# According to Appendix B of [1], the following are used in the Bench language +# (aka Benchnon, Gimira). In Bench, ⶻ is pronounced as /ʈ\u0361ʂʼ/ Retroflex +# ejective affricate; with a phonemic distrinction to the non-retroflex version. +# Amharic does not have retroflex phonemes, so we go with /t\u0361ʃʼ/. +ⶸ → t\u0361ʃʼə; +ⶹ → t\u0361ʃʼu; +ⶺ → t\u0361ʃʼi; +ⶻ → t\u0361ʃʼa; +ⶼ → t\u0361ʃʼe; +ⶽ → t\u0361ʃʼɨ; +ⶾ → t\u0361ʃʼo; +ቸ ↔ t\u0361ʃə; +ቹ ↔ t\u0361ʃu; +ቺ ↔ t\u0361ʃi; +ቻ ↔ t\u0361ʃa; +ቼ ↔ t\u0361ʃe; +ች ↔ t\u0361ʃɨ; +ቾ ↔ t\u0361ʃo; +ቿ ↔ t\u0361ʃwa; +ች ← t\u0361ʃ; +ተ ↔ tə; +ቱ ↔ tu; +ቲ ↔ ti; +ታ ↔ ta; +ቴ ↔ te; +ት ↔ tɨ; +ቶ ↔ to; +ⶆ → to; # Dizi, Me’en, Mursi, Suri /tɔ/ ([1], Appendix E); not used in Amharic. +ቷ ↔ twa; +ት ← t; +ጰ ↔ pʼə; +ጱ ↔ pʼu; +ጲ ↔ pʼi; +ጳ ↔ pʼa; +ጴ ↔ pʼe; +ጵ ↔ pʼɨ; +ጶ ↔ pʼo; +ⶑ → pʼo; # Dizi, Me’en, Mursi, Suri /pʼɔ/ ([1], Appendix E); not used in Amharic. +ጷ ↔ pʼwa; +ጵ ← pʼ; +ጸ ↔ sʼə; +ጹ ↔ sʼu; +ጺ ↔ sʼi; +ጻ ↔ sʼa; +ጼ ↔ sʼe; +ጽ ↔ sʼɨ; +ጾ ↔ sʼo; +ጿ ↔ sʼwa; +ጽ ← sʼ; +# In Amharic, ፀ is pronounced like ጸ. +# Source: [1], section on “Phonological Redundancy” for Amharic, page 5. +ፀ → sʼə; +ፁ → sʼu; +ፂ → sʼi; +ፃ → sʼa; +ፄ → sʼe; +ፅ → sʼɨ; +ፆ → sʼo; +ፇ → sʼo; # Dizi, Me’en, Mursi, Suri /sʼɔ/ ([1], Appendix E); not used in Amharic. +# Amharic speakers pronounce ሰ like ሠ. Source: [1], Appendix B. +ሰ ↔ sə; +ሱ ↔ su; +ሲ ↔ si; +ሳ ↔ sa; +ሴ ↔ se; +ስ ↔ sɨ; +ሶ ↔ so; +ⶃ → so; # Dizi, Me’en, Mursi, Suri /sɔ/ ([1], Appendix E); not used in Amharic. +ሷ ↔ swa; +ስ ← s; +ፈ ↔ fə; +ፉ ↔ fu; +ፊ ↔ fi; +ፋ ↔ fa; +ፌ ↔ fe; +ፍ ↔ fɨ; +ፎ ↔ fo; +ᎈ → fwə; # Sebatbeit /fwə/ ([1], Appendix H); not used in Amharic. +ᎉ → fwu; # Sebatbeit /fwu/ ([1], Appendix H); not used in Amharic. +ᎋ → fwi; # Sebatbeit /fwi/ ([1], Appendix H); not used in Amharic. +ፏ ↔ fwa; +ᎊ → fwe; # Sebatbeit /fwe/ ([1], Appendix H); not used in Amharic. +ፚ → fja; # Unclear which language; Appendix L of [1] transcribes ፚ as /fja/. +ፍ ← f; +ፐ ↔ pə; +ፑ ↔ pu; +ፒ ↔ pi; +ፓ ↔ pa; +ፔ ↔ pe; +ፕ ↔ pɨ; +ፖ ↔ po; +ⶒ → po; # Dizi, Me’en, Mursi, Suri /pɔ/ ([1], Appendix E); not used in Amharic. +ᎌ → pwə; # Sebatbeit /pwə/ ([1], Appendix H); not used in Amharic. +ᎍ → pwu; # Sebatbeit /pwu/ ([1], Appendix H); not used in Amharic. +ᎏ → pwi; # Sebatbeit /pwi/ ([1], Appendix H); not used in Amharic. +ፗ ↔ pwa; +ᎎ → pwe; # Sebatbeit /pwe/ ([1], Appendix H); not used in Amharic. +ፕ ← p; +ኧ ↔ ə; +ኡ ← u; # ኡላዓን ባዓታር ← Ulaan Baatar /ulaʕan baʕatar/ +አ ← a; # አምስተርዳም ← Amsterdam /amstərdam/ +ኤ ← e; +እ ← ɨ; +ኦ ← o; # ፖርት ኦፍ ስፔን ← Port of Spain /port of speːn/ +ኢ ← i; # ኢስላማባድ ← Islamabad /islamabad/ +# Applications will typically split words before calling our rules. +# To be resilient, we replace punctuation by whitespace in IPA. +፠ → ' '; # U+1360 ETHIOPIC SECTION MARK +፡ → ' '; # U+1361 ETHIOPIC WORDSPACE +። → ' '; # U+1362 ETHIOPIC FULL STOP +፣ → ' '; # U+1363 ETHIOPIC COMMA +፤ → ' '; # U+1364 ETHIOPIC SEMICOLON +፥ → ' '; # U+1365 ETHIOPIC COLON +፦ → ' '; # U+1366 ETHIOPIC PREFACE COLON +፧ → ' '; # U+1367 ETHIOPIC QUESTION MARK +፨ → ' '; # U+1368 ETHIOPIC PARAGRAPH SEPARATOR +# Likewise, Ethiopic numerals cannot be pronounced by these rules, +# so we replace them by whitespace in the output IPA notation. +# Applications will typically pre-process text before calling +# the am → am_FONIPA transform. +፩ → ' '; # U+1369 ETHIOPIC DIGIT ONE +፪ → ' '; # U+136A ETHIOPIC DIGIT TWO +፫ → ' '; # U+136B ETHIOPIC DIGIT THREE +፬ → ' '; # U+136C ETHIOPIC DIGIT FOUR +፭ → ' '; # U+136D ETHIOPIC DIGIT FIVE +፮ → ' '; # U+136E ETHIOPIC DIGIT SIX +፯ → ' '; # U+136F ETHIOPIC DIGIT SEVEN +፰ → ' '; # U+1370 ETHIOPIC DIGIT EIGHT +፱ → ' '; # U+1371 ETHIOPIC DIGIT NINE +፲ → ' '; # U+1372 ETHIOPIC NUMBER TEN +፳ → ' '; # U+1373 ETHIOPIC NUMBER TWENTY +፴ → ' '; # U+1374 ETHIOPIC NUMBER THIRTY +፵ → ' '; # U+1375 ETHIOPIC NUMBER FORTY +፶ → ' '; # U+1376 ETHIOPIC NUMBER FIFTY +፷ → ' '; # U+1377 ETHIOPIC NUMBER SIXTY +፸ → ' '; # U+1378 ETHIOPIC NUMBER SEVENTY +፹ → ' '; # U+1379 ETHIOPIC NUMBER EIGHTY +፺ → ' '; # U+137A ETHIOPIC NUMBER NINETY +፻ → ' '; # U+137B ETHIOPIC NUMBER HUNDRED +፼ → ' '; # U+137C ETHIOPIC NUMBER TEN THOUSAND +# Transform IPA length markers to one of these: +# U+135D ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK +# U+135E ETHIOPIC COMBINING VOWEL LENGTH MARK +# U+135F ETHIOPIC COMBINING GEMINATION MARK +::null(); +← ː ; # Strip off any remaining IPA length markers. +::(null); +($IPA_CONSONANT) ([jw]? $IPA_VOWEL) \u135D → $1 ː $2 ː; +($IPA_CONSONANT) ([jw]? $IPA_VOWEL) \u135E → $1 $2 ː; +($IPA_CONSONANT) ([jw]? $IPA_VOWEL?) \u135F → $1 ː $2; +[\u135D \u135E \u135F] → ; # Strip off any remaining length markers. +$1 wa \u135D ← ($LABIALIZABLE_BEFORE_A) ː waː; # ቷ\u135D ← [tːʷaː] +$1 wa \u135E ← ($LABIALIZABLE_BEFORE_A) waː; # ቷ\u135E ← [tʷaː] +$1 wa \u135F ← ($LABIALIZABLE_BEFORE_A) ː wa; # አቷ\u135F ← [tːʷa] +$1 \u135F $2 \u135E ← ([b $LABIALIZABLE_BEFORE_A]) ː ([jw] $IPA_VOWEL) ː; +$1 \u135F $2 ← {([b $LABIALIZABLE_BEFORE_A]) ː ([jw] $IPA_VOWEL?)}; +$1 \u135E ← ($IPA_VOWEL ː); +$1 \u135D ← (jː $IPA_VOWEL ː); +$1 \u135E ← ([jw] $IPA_VOWEL ː); +$1 \u135F ← (jː $IPA_VOWEL?); +$1 \u135D ← ($IPA_CONSONANT ː [w]? $IPA_VOWEL ː); +$1 \u135E ← ($IPA_CONSONANT [w]? $IPA_VOWEL ː); +$1 \u135F ← ($IPA_CONSONANT ː [w]? $IPA_VOWEL?); +# Insert syllable markers in a separate pass. +::null; +{($IPA_VOWEL ː?)} [[:L:]] → $1 \.; +::(null); +← [ˈˌ\. \u0303\u032F]; +aj ← ai; # Nairobi /nairobi/ ናይሮቢ, Cairo /kairo/ ካይሮ +aw ← au; # Bissau /bisːau/ ቢሳው +eji ← ei; # Beijing /beid\u0361ʒiŋ/ ቤዪጂንግ +ewo ← eo; # Montevideo /montevideo/ ሞንቴቪዴዎ +ija ← ia; # Monrovia /monrovia/ ሞንሮቪያ +ijə ← iə; # Reunion /rijunijən/ ሪዩኒየን +iw ← iu; # Vilnius /vilnius/ ቪልኒውስ, New Delhi /niu deːli/ ኒው ዴሊ +jo ← io; # Tokyo /tokio/ ቶክዮ +nɡ ← ŋɡ; # Kongo /koŋɡo/ ኮንጎ, Hungary /həŋɡari/ ሀንጋሪ +nɡ ← ŋ; # Bangkok /baŋkok/ ባንግኮክ, Beijing /beid\u0361ʒiŋ/ ቤዪጂንግ +uwa ← ua; # Kuala Lumpur /kuala lumpur/ ኩዋላ ሉምፑር, Ruanda /ruanda/ ሩዋንዳ +bwe ← bue; # Buenos Aires /buenos aires/ ብዌኖስ አይሬስ +sʼ ← t\u0361s; # Podgorica /podɡorit\u0361sa/ ፖድጎሪጻ, Vaduz /fadut\u0361s/ ፋዱጽ +uwi ← ui; # Port Luis /port luis/ ፖርት ሉዊስ +uwe ← ue; # Lithuania /lituenia/ ሊቱዌኒያ, Venezuela /venɨzuela/ ቬንዙዌላ +::(null); +ʔə ← \. ə; +ʔu ← \. u; +ʔi ← \. i; +ʔa ← \. a; +ʔe ← \. e; +ʔɨ ← \. ɨ; +ʔo ← \. o; +$1 w ← {($IPA_VOWEL ː?) \u032F} $IPA_VOWEL; # /ewowa/ ← /e\u032Fo\u032Fa/ +::(null); +n ← [n {n\u033C} {n\u033C\u030A} {m\u033A} {n\u030A} {n\u0325} ⁿ ᵑ]; +m ← [ɱ {m\u0325} {m\u032A} ᵐ]; +ɲ ← [{ɳ\u030A} {ɳ\u0325} ɳ {ɲ\u030A} {ɲ\u0325} ɲ]; +ŋ ← [{ŋ\u030A} {ŋ\u0325} ŋ]; +ɴ ← [{ɴ\u030A} {ɴ\u0325} ɴ]; +p ← [{t\u033C} {p\u033A}]; +pʼ ← [ʘ ɋ]; +b ← [{d\u033C} {b\u033A} {ɾ\u033C} ɓ]; +t ← [{t\u032A} ʈ]; +tʼ ← [ǁ ʖ]; +d ← [ɖ ɗ ᶑ]; +k ← q; +kʼ ← [ǃ ʗ]; +ɡ ← [g ɢ ɣ ɠ ʛ]; +nɡ ← ᵑɡ; +ʔ ← ʡ; +s ← [θ {θ\u0331} {θ\u031E} {θ\u033C} {ɸ\u033A}]; +z ← [ð {ð\u0320} {ð\u033C} {β\u033A}]; +sʼ ← [{t\u0361s} {t\u035Cs} ʦ]; +t\u0361ʃ ← [{t\u035Cʃ} ʧ {t\u0361ɕ} {t\u035Cɕ} ʨ {ʈ\u0361ʂ} c]; +t\u0361ʃʼ ← [ǀ ʇ ǂ ʄ]; +d\u0361ʒ ← [ʤ ʣ {d\u0361z} {d\u035Cz} {d\u0361ɕ} ʥ {d\u0361ʑ} {d\u035Cʑ} {ɖ\u0361ʐ} {d\u0361ʐ} ɟ]; +pf ← [{p\u032A} {p\u0346} ȹ {p\u0361f} {p\u032Af} {p\u032A\u035Cf}]; +bv ← [{b\u032A} {b\u0346} ȸ {b\u0361v} {b\u032A\u0361v}]; +ʃ ← [ʂ ɕ]; +ʒ ← [ʐ ʑ]; +r ← [ɾ ɽ ʁ]; +rːʒ ← r\u031Dː; +rʒ ← r\u031D; +v ← β; +x ← [ç x χ]; +ʕ ← ʕ\u031D; +h ← ɦ; +j ← [ʝ ʲ]; +lj ← ʎ [iɨ]? [jʝʲ]?; +t\u0361ʃl ← [{t\u0361ɬ} {tɬ}]; +ʃl ← ɬ; +w ← {u\u032F} $IPA_VOWEL; +w ← ʷ; +ʼː ← ːʼ; # /pʼː/ ← /pːʼ/; /sʼː/ ← /sːʼ/; etc. +::(null); +i ← y; +ɨ ← [ɪ ʉ]; +u ← [ʊ ɯ]; +ə ← [ɛ æ ɘ]; +o ← [ɔ ø]; +a ← ɑ; +ʼ ← ʰ; +← [ʱ]; +$1ːʲ ← ([pbtd])ʲː; # [bːʲeː] ← [bʲːeː] +$1ːʷ ← ([pbtd])ʷː; # [bːʷeː] ← [bʷːeː] +::(NFC); +← [ \u0303 \u0330 \u030B \u0301 \u0304 \u0300 \u030F \u030C \u0302 ˥ ˦ ˧ ˨ ˩ ꜜ ꜛ ↗ ↘ ]; +::(NFD); + |