Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Unverified Commit 2f96e534 authored by Alexander Epaneshnikov's avatar Alexander Epaneshnikov Committed by GitHub
Browse files

Add Shavian alphabet support (English) (#1924) 

This PR adds support for **Shavian**, a phonemic alphabet for English:
https://en.wikipedia.org/wiki/Shavian_alphabet (Unicode
[U+10450–U+1047F](https://www.unicode.org/charts/PDF/U10450.pdf); ISO
15924 - Shaw)
It correctly pronounces most English words, except sometimes it
misplaces the word stress. All checks are passing.
There are many Shavian communities online; I wanted to join in without
excluding people using screen readers.
If needed, this website has more resources: https://shavian.info/
![Screenshot of GNOME terminal, showing the difference between phonemes
in "This is an example sentence in the Shavian alphabet", and the same
sentence but for
Latin](https://github.com/espeak-ng/espeak-ng/assets/113068485/75d43247-1b70-4c16-8e55-6a9ffab7784d)

Continuation of #1818 due to an issue in a rebase
parents a7295c1e f69dd80b

ChangeLog.md

+1 −0
Original line number Diff line number Diff line
@@ -39,6 +39,7 @@ updated languages: 
*  uz (Uzbek) -- Andiv06



new languages:

*  en-Shaw (English, Shavian script) -- Luna Rose

*  ti (Tigrinya) -- Biniam Gebremichael

*  mto (Totontepec Mixe) -- Bill Dengler, Elizabeth Resendiz

*  fo (Faroese) -- Andras Eliassen, iSolveIT ApS and Setur.fo/Ravnur

dictsource/en_list

+79 −0
Original line number Diff line number Diff line
@@ -3372,6 +3372,7 @@ shampoo $2 
shaoni	SaI'oUni

shareable	Se@@b@L

sharpie		$alt2

shavian		$alt6

shazam		$alt3

shea S'eI $only

shebang		SI#baN
@@ -5708,3 +5709,81 @@ sterile $alt2 
tensile		$alt2

virile		$alt2

?3 volatile	v0la#t@L







// Shavian (phonemic alphabet for English)

// Community Shavian letter names

𐑐	p'In

𐑚	b'El

_𐑑	t'an

𐑛	d'Vn

𐑒	k'i:

𐑜	g'Il

_𐑓	f'eI

_𐑝	v'aI

𐑔	T'O@n

_𐑞	D'aU

𐑕	s'i:

𐑟	z'u:

𐑖	S'aI

𐑠	Z'oU

𐑗	tS'A:

𐑡	dZ'OI

𐑘	j'En

_𐑢	w'eI

𐑙	s'0N

𐑣	h'u:

𐑤	l'am

𐑮	r'oU

𐑥	m'i:

_𐑯	n'aU

𐑦	'In

𐑰	'i:v

𐑧	'EdZ

𐑱	'eIm

𐑨	'aS

_𐑲	'aIz

_𐑩	@g'oU

𐑳	'Vp

𐑪	'0n

_𐑴	'oUT

𐑫	'Umf

_𐑵	'u:z

𐑬	'aUns

𐑶	'OIl

𐑭	'A:mz

𐑷	'O:t

_𐑸	'a:ri;@

_𐑹	'O:r@

𐑻	'3:rlI

𐑼	@r'eI

_𐑽	'i@3ri

𐑾	'i:;@n

_𐑿	j'u:l



// Shavian short forms and single letter words

𐑩	$nounf

𐑸	%A@		$pastf $only

𐑲	aI		$u+ $verbf $only

𐑯	and		$u $pause $only

𐑞	D@2		$only $nounf

𐑓	fO@		$u

𐑽	i@3		$noun

𐑿	ju:		$u $verbf

𐑴	'oU

𐑵	'u:		// "ooh"

𐑹	O@		$u $pause $only

𐑝	02v		$u $only

𐑑	t@5		$verbf $alt7    // @ change to U before vowel

𐑢	wID		$u   // used sometimes



// Shavian dictionary

𐑥𐑲	maI 	$u $nounf $strend2

𐑦𐑯	%In 	$strend $only $nounf

𐑦𐑟	%Iz 	$pastf $only

𐑣𐑨𐑛	%had	$pastf $strend2 $only

𐑖𐑰	Si: 	$u $only $verbsf

𐑕𐑳𐑥	,sVm	$nounf $unstressend $only

𐑚𐑳𐑑	,bVt	$pause $only

𐑢𐑦𐑗	,wItS	$pause $strend2 $only $verbf

dictsource/en_rules

+53 −1
Original line number Diff line number Diff line
@@ -6986,9 +6986,61 @@ contin) u ju: 
        'd (_S2    d

        'll (_S3   @L



// Shavian characters, phonemic alphabet for English

.group 0xF0

// 0xF0 is the first byte of the utf-8 code for these characters



    𐑐     p

    𐑚     b

    𐑑     t

    𐑛     d

    𐑒     k

    𐑜     g

    𐑓     f

    𐑝     v

    𐑔     T

    𐑞     D

    𐑕     s

    𐑟     z

    𐑖     S

    𐑠     Z

    𐑗     tS

    𐑡     dZ

    𐑘     j

    𐑢     w

    𐑙     N

    𐑣     h

    𐑤     l

    𐑮     r

    𐑥     m

    𐑯     n

    𐑦     I

    𐑦 (_  %i

    𐑰     i:

    𐑧     E

    𐑱     eI

    𐑨     a

    𐑲     aI

    𐑩     @

    𐑳     V

    𐑪     0

    𐑴     oU

    𐑫     U

    𐑵     u:

    𐑬     aU

    𐑶     OI

    𐑭     A:

    𐑷     O:

    𐑸     'A@

    𐑹     'O@

    𐑺     'e@

    𐑻     '3:

    𐑼     3

    𐑽     'i@3

    𐑾     i:@

    𐑿     ju:



.group 0xce   // Greek letters

// 0xce is the first byte of the utf-8 code for these characters



        α          'alf@_

        β          b'i:t@_

espeak-ng-data/lang/gmw/en-Shaw

0 → 100644
+5 −0
Original line number Diff line number Diff line 
name English (Shavian alphabet)

language en-shaw

maintainer Luna Rose <luna@anarchy.center>

status testing

phonemes en

src/libespeak-ng/tr_languages.c

+2 −0
Original line number Diff line number Diff line
@@ -59,6 +59,7 @@ 
#define OFFSET_GEORGIAN 0x10a0

#define OFFSET_KOREAN   0x1100

#define OFFSET_ETHIOPIC 0x1200

#define OFFSET_SHAVIAN  0x10450



// character ranges must be listed in ascending unicode order

static const ALPHABET alphabets[] = {
@@ -89,6 +90,7 @@ static const ALPHABET alphabets[] = { 
	{ "_ja",    0x3040,          0x3040, 0x30ff, 0, AL_NOT_CODE },

	{ "_zh",    0x3100,          0x3100, 0x9fff, 0, AL_NOT_CODE },

	{ "_ko",    0xa700,          0xa700, 0xd7ff, L('k', 'o'), AL_NOT_CODE | AL_WORDS },

	{ "_shaw",  OFFSET_SHAVIAN,  0x10450, 0x1047F, L('e', 'n'), 0 },

	{ NULL, 0, 0, 0, 0, 0 }

};