| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485 |
- #!/bin/sh
-
- test_phonemes() {
- TEST_LANG=$1
- EXPECTED=$2
- TEST_TEXT=$3
-
- echo "testing ${TEST_LANG} \"${TEST_TEXT}\""
- ESPEAK_DATA_PATH=`pwd` LD_LIBRARY_PATH=src:${LD_LIBRARY_PATH} \
- src/espeak-ng -xq -v ${TEST_LANG} "${TEST_TEXT}" > actual.txt
- echo "${EXPECTED}" > expected.txt
- diff expected.txt actual.txt || exit 1
- }
-
- # word lookup
- test_phonemes en "h@l'oU" "hello"
-
- # correct word stress
- test_phonemes en "s'VmTIN Imp'o@t@nt" "something important"
-
- # suffix rules
- test_phonemes lv \
- "nev'ie:na nuo\`_ 'eiRo:pas v'alsti:m nek,ad nav p'a:Rga:jusi nuo\`_ 'univERsa:la:s_:_: nuo\` v'ispa:Re:jiem n'uoduok_|l^iem f'inanse:tas_:_: s'iste:mas uz 'obliga:ta:s 'apdRuoSina:Sanas s'iste:mu b'eigas" \
- "Neviena no Eiropas valstīm nekad nav pārgājusi no universālās (no vispārējiem nodokļiem finansētas) sistēmas uz obligātās apdrošināšanas sistēmu Beigas."
-
- # A list entry that uses '$text' to map to another list entry crashes 1.49.2 multi-word support:
- test_phonemes en "d'eIbju:tI2d" "débuted"
- test_phonemes en-US "d'eIbju:t#I#d" "débuted"
-
- # s at the end of abbreviations
- # https://github.com/espeak-ng/espeak-ng/issues/706
- test_phonemes en ",aIb,i:;'Em m'It 'Ib@mz m'Its ,aIb,i:;'Em ,Em,aIt'i:; ,eIp,i:;'eItS s,i:;,i:;'Es ,aIt,i:;'Eks ,aIb,i:;'Emz ,Em,aIt'i:z ,eIp,i:;'eItSIz s,i:;,i:;'EsIz ,aIt,i:;'EksIz" "ibm mit ibms mits IBM MIT APH CES ITX IBMs MIT's APHs CES's ITXs"
- test_phonemes lv "'ibm m'it 'ibm-s m'its 'ibm m'it 'aph ts'Es 'it_ks 'ibm-s m'its 'aphs ts'Ess 'it_kss" "ibm mit ibms mits IBM MIT APH CES ITX IBMs MIT's APHs CES's ITXs"
- test_phonemes ru "(en),aIb,i:;'Em m'It 'Ib@mz m'Its ,aIb,i:;'Em ,Em,aIt'i:; ,eIp,i:;'eItS s,i:;,i:;'Es ,aIt,i:;'Eks 'Ib@mz m'Its 'afz s'EI2zI2z 'ItEksz(ru)" "ibm mit ibms mits IBM MIT APH CES ITX IBMs MIT's APHs CES's ITXs"
-
- # bug: https://github.com/nvaccess/nvda/issues/7740
- test_phonemes ta "'il." "ள்"
- test_phonemes my "kon'i" "7"
- test_phonemes ka "s'ami Sv'idi" "3 7"
-
- # bug: https://github.com/nvaccess/nvda/issues/7805
- test_phonemes hi "r'UcI" "रुचि"
- test_phonemes hi "dUk'a:n" "दुकान"
- test_phonemes hi "ka:n'u:n" "कानून"
-
- # A deleted phoneme at the start of a word should preserve the sourceix property.
- test_phonemes en-GB-x-gbcwmd "aI 'av" "I have"
-
- # A deleted phonSWITCH should preserve the sourceix property of the deleted phoneme.
- test_phonemes hyw "'a g@rn'am" "A Կրնամ"
-
- test_phonemes en "'eI
- b'i: s'i:
- d'i:
- 'i:
- 'Ef" "A. B C, D. E: F."
-
- # Handling of english acronym + genitive without breaking simple quote
- test_phonemes en "hi: s'Ed
- aI w0z b'O@n InD@ j,u:,Es'eI z_:_: and l'Eft" "He said : I was born in the u.s.a.'s and left."
-
- test_phonemes en "hi: s'Ed
- h@l'oU
- aIa#m b'ak
- and l'Eft" "He said : 'Hello, I am back.' and left."
-
- #----- Emoji [http://www.unicode.org/reports/tr51/tr51-12.html] -----
-
- # ED-3 - emoji_character
- test_phonemes en "'e@ri:z" "♈"
- test_phonemes my "pru3'a2nke3DN_|_| mj@@lu3'a2mj@2tsnh,a2N_|_| nm_|n'e3DN_|_| mj@@nh,ats" "😙"
- test_phonemes ka "k'ots#nis g'amomx,atveli s'axe m'omQim,are t#v'alebit#" "😙"
- test_phonemes ka "'imedg,ats#ru,ebuli m'agram Sv'ebis g'amomx,atveli s'axe" "😥"
- # TODO: Fix adjacent emoji without whitespace so the pronunciation is separated by a space.
- test_phonemes en "'e@ri:zr'eInboU" "♈🌈"
- test_phonemes en "'e@ri:z r'eInboU" "♈ 🌈"
-
- # multi-word emoji
- test_phonemes en "Ekskla#m'eIS@n kw'EstS@n m'A@k" "⁉"
- test_phonemes en "Ekskla#m'eIS@n kw'EstS@n m'A@k r'eInboU" "⁉ 🌈"
- test_phonemes en "r'oUlIN 0nD@ fl'o@ l'aafIN" "🤣" # skip words
-
- # bug: https://github.com/espeak-ng/espeak-ng/issues/471
- test_phonemes sk "sm'eju:tsa s'a tv'a:R" "☺"
- test_phonemes sk "bl'ax sm'eju:tsa s'a tv'a:R" "blah ☺"
|
