This is a version (not official) of the full grammar of Lojban. I intend to make many changes to it, some cosmetic, some not. Don't take the contents of this page too seriously for now. In zasni gerna cenba vreji I will try to keep a record of the changes as I make them. mi'e xorxes
; - GRAMMAR -
PUBLIC text <- intro-null indicators? (!gek joik-jek)? text-1? FAhO#? EOF?
SPACE intro-null <- SU-NULL# SI-NULL# SI#*
text-1 <- I# joik-jek? (tag? BO#)? text-1? / NIhO#+ SU-NULL# paragraphs? / paragraphs
paragraphs <- paragraph (NIhO#+ SU-NULL# paragraph)*
paragraph <- statement (I# statement?)*
statement <- statement-1 / prenex statement / fragment
statement-1 <- statement-2 (I# joik-jek statement-2?)*
statement-2 <- statement-3 (I# joik-jek? tag? BO# statement-2)? / statement-3 (I# joik-jek? tag? BO#)?
statement-3 <- sentence / tag? TUhE# text-1 TUhU#?
fragment <- prenex / terms VAU#? / ek / gihek / quantifier / NA# !JA# / relative-clauses / links / linkargs
prenex <- terms ZOhU#
sentence <- (terms CU#?)? bridi-tail
subsentence <- sentence / prenex subsentence
bridi-tail <- bridi-tail-1 (gihek tag? KE# bridi-tail KEhE#? tail-terms)?
bridi-tail-1 <- bridi-tail-2 (gihek !(tag? KE#) bridi-tail-2 tail-terms)*
bridi-tail-2 <- bridi-tail-3 (gihek tag? BO# bridi-tail-2 tail-terms)?
bridi-tail-3 <- selbri tail-terms / gek-sentence
gek-sentence <- gek subsentence gik subsentence tail-terms / tag? KE# gek-sentence KEhE#? / NA# gek-sentence
tail-terms <- terms? VAU#?
terms <- terms-1+
terms-1 <- terms-2 (PEhE# joik-jek terms-2)*
terms-2 <- term (CEhE# term)*
term <- FA#? sumti / tag? sumti / tag KU#? / FA# KU#? / NA# KU# / termset
termset <- gek-termset / NUhI# gek terms NUhU#? gik terms NUhU#? / NUhI# terms NUhU#?
gek-termset <- gek terms-gik-terms
terms-gik-terms <- term (gik / terms-gik-terms) term
sumti <- sumti-1 (VUhO# relative-clauses)?
sumti-1 <- sumti-2 (joik-ek tag? KE# sumti KEhE#?)?
sumti-2 <- sumti-3 (joik-ek sumti-3)*
sumti-3 <- sumti-4 (joik-ek tag? BO# sumti-3)?
sumti-4 <- sumti-5 / gek sumti gik sumti-4
sumti-5 <- quantifier? sumti-6 relative-clauses? / quantifier selbri KU#? relative-clauses?
sumti-6 <- ZO-WORD# / ZOI-EXPRESSION# / LOhU-WORDS# / lerfu-string !MOI# BOI#? / LU# text LIhU#? / (LAhE# / NAhE# BO#) relative-clauses? sumti LUhU#? / KOhA# / (LA# / LE#) sumti-tail KU#? / LI# mex LOhO#?
sumti-tail <- sumti-6? relative-clauses? (quantifier? selbri relative-clauses? / quantifier sumti)
relative-clauses <- relative-clause (ZIhE# relative-clause)*
relative-clause <- GOI# term GEhU#? / NOI# subsentence KUhO#?
selbri <- (tag / NA#)* selbri-2
selbri-2 <- selbri-4+ (CO# selbri-2)?
selbri-4 <- selbri-5 (joik-jek selbri-5 / joik-jek tag? KE# selbri-4+ KEhE#?)*
selbri-5 <- selbri-6 (joik-jek tag? BO# selbri-5)?
selbri-6 <- tanru-unit (BO# selbri-6)? / NAhE#? guhek selbri gik selbri-6
tanru-unit <- tanru-unit-1 (CEI# tanru-unit-1)*
tanru-unit-1 <- tanru-unit-2 linkargs?
tanru-unit-2 <- BRIVLA# / ZEI-LUJVO# / CMENE# / GOhA# / KE# selbri-4+ KEhE#? / ME# (sumti / lerfu-string) MEhU#? MOI#? / (number / lerfu-string) MOI# / NUhA# mex-operator / SE# tanru-unit-2 / JAI# tag? tanru-unit-2 / NAhE# tanru-unit-2 / NU# (joik-jek NU#)* subsentence KEI#?
linkargs <- BE# term links? BEhO#?
links <- BEI# term links?
quantifier <- number !MOI# BOI#? / VEI# mex VEhO#?
mex <- mex-1 (operator mex-1)* / rp#
rp# <- FUhA# rp-expression
mex-1 <- mex-2 (BIhE# operator mex-1)?
mex-2 <- operand / mex-forethought
mex-forethought <- PEhO#? operator fore-operands KUhE#?
fore-operands <- mex-2+
rp-expression <- operand (rp-expression operator)*
operator <- operator-1 (joik-jek operator-1 / joik-jek tag? KE# operator KEhE#?)*
operator-1 <- operator-2 / guhek operator-1 gik operator-2 / operator-2 joik-jek tag? BO# operator-1
operator-2 <- mex-operator / KE# operator KEhE#?
mex-operator <- SE# mex-operator / NAhE# mex-operator / MAhO# mex TEhU#? / NAhU# selbri TEhU#? / VUhU#
operand <- operand-1 (joik-ek tag? KE# operand KEhE#?)?
operand-1 <- operand-2 (joik-ek operand-2)*
operand-2 <- operand-3 (joik-ek tag? BO# operand-2)?
operand-3 <- quantifier / lerfu-string !MOI# BOI#? / NIhE# selbri TEhU#? / MOhE# sumti TEhU#? / JOhI# mex-2+ TEhU#? / gek operand gik operand-3 / (LAhE# / NAhE# BO#) operand LUhU#?
number <- PA#+
lerfu-string <- lerfu-word+
lerfu-word <- BY# / BU-LERFU# / LAU# lerfu-word / TEI# lerfu-string FOI#
ek <- NA#? SE#? A#
gihek <- NA#? SE#? GIhA#
joik-jek <- NA#? SE#? (JOI# / JA# / BIhI#)
joik-ek <- joik-jek / ek
gek <- SE#? GA# / joik-jek GI# / tag GI#
guhek <- SE#? GUhA#
gik <- GI#
tag <- tag-unit+ (joik-jek tag-unit+)*
tag-unit <- KI# / BAI# / PU# / ZI# / ZEhA# / FAhA# / VA# / VEhA# / VIhA# / TAhE# / ZAhO# / CAhA# / CUhE# / number ROI# / FIhO# selbri FEhU# / (FEhE# / MOhI# / SE# / NAhE#) tag-unit
; - Word Modifiers -
pre# <- BAhE#* SI-NULL# spaces?
post# <- !ZEI# !BU# indicators?
free <- SEI# (terms CU#?)? selbri SEhU#? / SOI# sumti sumti? SEhU#? / vocative / (number / lerfu-string) MAI# / TO# text TOI#? / XI# (number / lerfu-string) BOI#? / XI# VEI# mex VEhO#?
vocative <- (COI#+ DOI#? / DOI#) (relative-clauses? selbri relative-clauses? / sumti?) DOhU#?
indicators <- FUhE#? indicator+
indicator <- UI# / CAI# / NAI# / DAhO# / FUhO# / RAhO# / GAhO# / free
; - Magic Words -
LOhU-WORDS# <- pre# LOhU (!LEhU# any-word#)* LEhU#
ZO-WORD# <- pre# ZO any-word# post#
ZOI-EXPRESSION# <- pre# ZOI zoi-open zoi-word* zoi-close post#
BU-LERFU# <- pre# BU-LERFU !(lerfu-string MAI#) post#
ZEI-LUJVO# <- pre# ZEI-LUJVO post#
BU-LERFU <- zei-bu-word (bu-tail? zei-tail)* bu-tail
ZEI-LUJVO <- zei-bu-word (zei-tail? bu-tail)* zei-tail
zei-tail <- (ZEI# any-word#)+
bu-tail <- BU#+
zei-bu-word <- !BU# !ZEI# !SI# !SU# !FAhO# any-word#
SI-NULL# <- (si-word SI#)*
si-word <- (ZEI-LUJVO / BU-LERFU / !SI# !SU# !FAhO# any-word#)
SU-NULL# <- (su-word* SU#)*
su-word <- ZEI-LUJVO / BU-LERFU / !NIhO# !LU# !TUhE# !TO# !SU# !FAhO# any-word#
; - SELMAHO -
; - Special Cases -
any-word# <- spaces? any-word
SI# <- SI-NULL# spaces? SI
SU# <- SI-NULL# spaces? SU
BU# <- SI-NULL# spaces? BU
ZEI# <- SI-NULL# spaces? ZEI
BAhE# <- SI-NULL# spaces? BAhE
BY# <- pre# BY !(lerfu-string MAI#) post#
COI# <- pre# COI !vocative post#
PA# <- pre# PA !(number MAI#) post#
; - Normal Cases -
BRIVLA# <- pre# BRIVLA post#
CMENE# <- pre# CMENE post#
CMAVO# <- pre# CMAVO post#
A# <- pre# A post#
BAI# <- pre# BAI post#
BE# <- pre# BE post#
BEI# <- pre# BEI post#
BEhO# <- pre# BEhO post#
BIhE# <- pre# BIhE post#
BIhI# <- pre# BIhI post#
BO# <- pre# BO post#
BOI# <- pre# BOI post#
CAhA# <- pre# CAhA post#
CAI# <- pre# CAI post#
CEI# <- pre# CEI post#
CEhE# <- pre# CEhE post#
CO# <- pre# CO post#
CU# <- pre# CU post#
CUhE# <- pre# CUhE post#
DAhO# <- pre# DAhO post#
DOhU# <- pre# DOhU post#
DOI# <- pre# DOI post#
FA# <- pre# FA post#
FAhA# <- pre# FAhA post#
FAhO# <- pre# FAhO dot-star
FEhE# <- pre# FEhE post#
FEhU# <- pre# FEhU post#
FIhO# <- pre# FIhO post#
FOI# <- pre# FOI post#
FUhA# <- pre# FUhA post#
FUhE# <- pre# FUhE post#
FUhO# <- pre# FUhO post#
GA# <- pre# GA post#
GAhO# <- pre# GAhO post#
GEhU# <- pre# GEhU post#
GI# <- pre# GI post#
GIhA# <- pre# GIhA post#
GOI# <- pre# GOI post#
GOhA# <- pre# GOhA post#
GUhA# <- pre# GUhA post#
I# <- pre# I post#
JA# <- pre# JA post#
JAI# <- pre# JAI post#
JOhI# <- pre# JOhI post#
JOI# <- pre# JOI post#
KE# <- pre# KE post#
KEhE# <- pre# KEhE post#
KEI# <- pre# KEI post#
KI# <- pre# KI post#
KOhA# <- pre# KOhA post#
KU# <- pre# KU post#
KUhE# <- pre# KUhE post#
KUhO# <- pre# KUhO post#
LA# <- pre# LA post#
LAU# <- pre# LAU post#
LAhE# <- pre# LAhE post#
LE# <- pre# LE post#
LEhU# <- pre# LEhU post#
LI# <- pre# LI post#
LIhU# <- pre# LIhU post#
LOhO# <- pre# LOhO post#
LU# <- pre# LU post#
LUhU# <- pre# LUhU post#
MAhO# <- pre# MAhO post#
MAI# <- pre# MAI post#
ME# <- pre# ME post#
MEhU# <- pre# MEhU post#
MOhE# <- pre# MOhE post#
MOhI# <- pre# MOhI post#
MOI# <- pre# MOI post#
NA# <- pre# NA post#
NAI# <- pre# NAI post#
NAhE# <- pre# NAhE post#
NAhU# <- pre# NAhU post#
NIhE# <- pre# NIhE post#
NIhO# <- pre# NIhO post#
NOI# <- pre# NOI post#
NU# <- pre# NU post#
NUhA# <- pre# NUhA post#
NUhI# <- pre# NUhI post#
NUhU# <- pre# NUhU post#
PEhE# <- pre# PEhE post#
PEhO# <- pre# PEhO post#
PU# <- pre# PU post#
RAhO# <- pre# RAhO post#
ROI# <- pre# ROI post#
SE# <- pre# SE post#
SA# <- pre# SA post#
SEI# <- pre# SEI post#
SEhU# <- pre# SEhU post#
SOI# <- pre# SOI post#
TAhE# <- pre# TAhE post#
TEhU# <- pre# TEhU post#
TEI# <- pre# TEI post#
TO# <- pre# TO post#
TOI# <- pre# TOI post#
TUhE# <- pre# TUhE post#
TUhU# <- pre# TUhU post#
UI# <- pre# UI post#
VA# <- pre# VA post#
VAU# <- pre# VAU post#
VEI# <- pre# VEI post#
VEhO# <- pre# VEhO post#
VUhU# <- pre# VUhU post#
VEhA# <- pre# VEhA post#
VIhA# <- pre# VIhA post#
VUhO# <- pre# VUhO post#
XI# <- pre# XI post#
ZAhO# <- pre# ZAhO post#
ZEhA# <- pre# ZEhA post#
ZI# <- pre# ZI post#
ZIhE# <- pre# ZIhE post#
ZOhU# <- pre# ZOhU post#
;************************
; MORPHOLOGY INTERFACE
; This section handles the interface with the morphology. If you are not
; interested in this particular implementation of the morphology, you can
; ignore everything below this point and consider the above as the full
; formal grammar with terminals BRIVLA, CMENE, CMAVO, any-word,
; A, BAI, ..., ZOhU, zoi-open, zoi-word, zoi-close, spaces, dot-star and EOF.
;************************
zoi-open <- spaces? any-word &{ myAssign( new String(innerWordSEP2.toString()) ) }
zoi-word <- spaces? any-printable-word &{ ! myCompare( startString, innerWordSEP3 ) }
zoi-close <- spaces? any-word &{ myCompare( startString, innerWordSEP3 ) }
any-printable-word <- any-word / non-lojban-word
any-word <- CMENE / CMAVO / BRIVLA
ybu <- Y space-char* BU
lujvo <- !gismu !fuhivla brivla
;-----------------------
A <- &CMAVO ( a / e / j i / o / u ) &post-cmavo
BAI <- &CMAVO ( d u h o / s i h u / z a u / k i h i / d u h i / c u h u / t u h i / t i h u / d i h o / j i h u / r i h a / n i h i / m u h i / k i h u / v a h u / k o i / c a h i / t a h i / p u h e / j a h i / k a i / b a i / f i h e / d e h i / c i h o / m a u / m u h u / r i h i / r a h i / k a h a / p a h u / p a h a / l e h a / k u h u / t a i / b a u / m a h i / c i h e / f a u / p o h i / c a u / m a h e / c i h u / r a h a / p u h a / l i h e / l a h u / b a h i / k a h i / s a u / f a h e / b e h i / t i h i / j a h e / g a h a / v a h o / j i h o / m e h a / d o h e / j i h e / p i h o / g a u / z u h e / m e h e / r a i ) &post-cmavo
BAhE <- &CMAVO ( b a h e / z a h e ) &post-cmavo
BE <- &CMAVO ( b e ) &post-cmavo
BEI <- &CMAVO ( b e i ) &post-cmavo
BEhO <- &CMAVO ( b e h o ) &post-cmavo
BIhE <- &CMAVO ( b i h e ) &post-cmavo
BIhI <- &CMAVO ( m i h i / b i h o / b i h i ) &post-cmavo
BO <- &CMAVO ( b o ) &post-cmavo
BOI <- &CMAVO ( b o i ) &post-cmavo
BU <- &CMAVO ( b u ) &post-cmavo
BY <- ybu / &CMAVO ( j o h o / r u h o / g e h o / j e h o / l o h a / n a h a / s e h e / t o h a / g a h e / y h y / b y / c y / d y / f y / g y / j y / k y / l y / m y / n y / p y / r y / s y / t y / v y / x y / z y ) &post-cmavo
CAhA <- &CMAVO ( c a h a / p u h i / n u h o / k a h e ) &post-cmavo
CAI <- &CMAVO ( p e i / c a i / c u h i / s a i / r u h e ) &post-cmavo
CEI <- &CMAVO ( c e i ) &post-cmavo
CEhE <- &CMAVO ( c e h e ) &post-cmavo
CO <- &CMAVO ( c o ) &post-cmavo
COI <- &CMAVO ( j u h i / c o i / f i h i / t a h a / m u h o / f e h o / c o h o / p e h u / k e h o / n u h e / r e h i / b e h e / j e h e / m i h e / k i h e / v i h o ) &post-cmavo
CU <- &CMAVO ( c u ) &post-cmavo
CUhE <- &CMAVO ( c u h e / n a u ) &post-cmavo
DAhO <- &CMAVO ( d a h o ) &post-cmavo
DOI <- &CMAVO ( d o i ) &post-cmavo
DOhU <- &CMAVO ( d o h u ) &post-cmavo
FA <- &CMAVO ( f a i / f a / f e / f o / f u / f i h a / f i ) &post-cmavo
FAhA <- &CMAVO ( d u h a / b e h a / n e h u / v u h a / g a h u / t i h a / n i h a / c a h u / z u h a / r i h u / r u h u / r e h o / t e h e / b u h u / n e h a / p a h o / n e h i / t o h o / z o h i / z e h o / z o h a / f a h a ) &post-cmavo
FAhO <- &CMAVO ( f a h o ) &post-cmavo
FEhE <- &CMAVO ( f e h e ) &post-cmavo
FEhU <- &CMAVO ( f e h u ) &post-cmavo
FIhO <- &CMAVO ( f i h o ) &post-cmavo
FOI <- &CMAVO ( f o i ) &post-cmavo
FUhA <- &CMAVO ( f u h a ) &post-cmavo
FUhE <- &CMAVO ( f u h e ) &post-cmavo
FUhO <- &CMAVO ( f u h o ) &post-cmavo
GA <- &CMAVO ( g e h i / g e / g o / g a / g u ) &post-cmavo
GAhO <- &CMAVO ( k e h i / g a h o ) &post-cmavo
GEhU <- &CMAVO ( g e h u ) &post-cmavo
GI <- &CMAVO ( g i ) &post-cmavo
GIhA <- &CMAVO ( g i h e / g i h i / g i h o / g i h a / g i h u ) &post-cmavo
GOI <- &CMAVO ( n o h u / n e / g o i / p o h u / p e / p o h e / p o ) &post-cmavo
GOhA <- &CMAVO ( m o / n e i / g o h u / g o h o / g o h i / n o h a / g o h e / g o h a / d u / b u h a / b u h e / b u h i / c o h e ) &post-cmavo
GUhA <- &CMAVO ( g u h e / g u h i / g u h o / g u h a / g u h u ) &post-cmavo
I <- &CMAVO ( i ) &post-cmavo
JA <- &CMAVO ( j e h i / j e / j o / j a / j u ) &post-cmavo
JAI <- &CMAVO ( j a i ) &post-cmavo
JOhI <- &CMAVO ( j o h i ) &post-cmavo
JOI <- &CMAVO ( f a h u / p i h u / j o i / c e h o / c e / j o h u / k u h a / j o h e / j u h e ) &post-cmavo
KE <- &CMAVO ( k e ) &post-cmavo
KEhE <- &CMAVO ( k e h e ) &post-cmavo
KEI <- &CMAVO ( k e i ) &post-cmavo
KI <- &CMAVO ( k i ) &post-cmavo
KOhA <- &CMAVO ( d a h u / d a h e / d i h u / d i h e / d e h u / d e h e / d e i / d o h i / m i h o / m a h a / m i h a / d o h o / k o h a / f o h u / k o h e / k o h i / k o h o / k o h u / f o h a / f o h e / f o h i / f o h o / v o h a / v o h e / v o h i / v o h o / v o h u / r u / r i / r a / t a / t u / t i / z i h o / k e h a / m a / z u h i / z o h e / c e h u / d a / d e / d i / k o / m i / d o ) &post-cmavo
KU <- &CMAVO ( k u ) &post-cmavo
KUhE <- &CMAVO ( k u h e ) &post-cmavo
KUhO <- &CMAVO ( k u h o ) &post-cmavo
LA <- &CMAVO ( l a i / l a h i / l a ) &post-cmavo
LAU <- &CMAVO ( c e h a / l a u / z a i / t a u ) &post-cmavo
LAhE <- &CMAVO ( t u h a / l u h a / l u h o / l a h e / v u h i / l u h i / l u h e ) &post-cmavo
LE <- &CMAVO ( l e i / l o i / l e h i / l o h i / l e h e / l o h e / l o / l e ) &post-cmavo
LEhU <- &CMAVO ( l e h u ) &post-cmavo
LI <- &CMAVO ( m e h o / l i ) &post-cmavo
LIhU <- &CMAVO ( l i h u ) &post-cmavo
LOhO <- &CMAVO ( l o h o ) &post-cmavo
LOhU <- &CMAVO ( l o h u ) &post-cmavo
LU <- &CMAVO ( l u ) &post-cmavo
LUhU <- &CMAVO ( l u h u ) &post-cmavo
MAhO <- &CMAVO ( m a h o ) &post-cmavo
MAI <- &CMAVO ( m o h o / m a i ) &post-cmavo
ME <- &CMAVO ( m e ) &post-cmavo
MEhU <- &CMAVO ( m e h u ) &post-cmavo
MOhE <- &CMAVO ( m o h e ) &post-cmavo
MOhI <- &CMAVO ( m o h i ) &post-cmavo
MOI <- &CMAVO ( m e i / m o i / s i h e / c u h o / v a h e ) &post-cmavo
NA <- &CMAVO ( j a h a / n a ) &post-cmavo
NAI <- &CMAVO ( n a i ) &post-cmavo
NAhE <- &CMAVO ( t o h e / j e h a / n a h e / n o h e ) &post-cmavo
NAhU <- &CMAVO ( n a h u ) &post-cmavo
NIhE <- &CMAVO ( n i h e ) &post-cmavo
NIhO <- &CMAVO ( n i h o / n o h i ) &post-cmavo
NOI <- &CMAVO ( v o i / n o i / p o i ) &post-cmavo
NU <- &CMAVO ( n i / d u h u / s i h o / n u / l i h i / k a / j e i / s u h u / z u h o / m u h e / p u h u / z a h i ) &post-cmavo
NUhA <- &CMAVO ( n u h a ) &post-cmavo
NUhI <- &CMAVO ( n u h i ) &post-cmavo
NUhU <- &CMAVO ( n u h u ) &post-cmavo
PA <- &CMAVO ( d a u / f e i / g a i / j a u / r e i / v a i / p i h e / p i / f i h u / z a h u / m e h i / n i h u / k i h o / c e h i / m a h u / r a h e / d a h a / s o h a / j i h i / s u h o / s u h e / r o / r a u / s o h u / s o h i / s o h e / s o h o / m o h a / d u h e / t e h o / k a h o / c i h i / t u h o / x o / p a i / n o h o / n o / p a / r e / c i / v o / m u / x a / z e / b i / s o / digit ) &post-cmavo
PEhE <- &CMAVO ( p e h e ) &post-cmavo
PEhO <- &CMAVO ( p e h o ) &post-cmavo
PU <- &CMAVO ( b a / p u / c a ) &post-cmavo
RAhO <- &CMAVO ( r a h o ) &post-cmavo
ROI <- &CMAVO ( r e h u / r o i ) &post-cmavo
SA <- &CMAVO ( s a ) &post-cmavo
SE <- &CMAVO ( s e / t e / v e / x e ) &post-cmavo
SEI <- &CMAVO ( s e i / t i h o ) &post-cmavo
SEhU <- &CMAVO ( s e h u ) &post-cmavo
SI <- &CMAVO ( s i ) &post-cmavo
SOI <- &CMAVO ( s o i ) &post-cmavo
SU <- &CMAVO ( s u ) &post-cmavo
TAhE <- &CMAVO ( r u h i / t a h e / d i h i / n a h o ) &post-cmavo
TEhU <- &CMAVO ( t e h u ) &post-cmavo
TEI <- &CMAVO ( t e i ) &post-cmavo
TO <- &CMAVO ( t o h i / t o ) &post-cmavo
TOI <- &CMAVO ( t o i ) &post-cmavo
TUhE <- &CMAVO ( t u h e ) &post-cmavo
TUhU <- &CMAVO ( t u h u ) &post-cmavo
UI <- &CMAVO ( i h a / i e / a h e / u h i / i h o / i h e / a h a / i a / o h i / o h e / e h e / o i / u o / e h i / u h o / a u / u a / a h i / i h u / i i / u h a / u i / a h o / a i / a h u / i u / e i / o h o / e h a / u u / o h a / o h u / u h u / e h o / i o / e h u / u e / i h i / u h e / b a h a / j a h o / c a h e / s u h a / t i h e / k a h u / s e h o / z a h a / p e h i / r u h a / j u h a / t a h o / r a h u / l i h a / b a h u / m u h a / d o h a / t o h u / v a h i / p a h e / z u h u / s a h e / l a h a / k e h u / s a h u / d a h i / j e h u / s a h a / k a u / t a h u / n a h i / j o h a / b i h u / l i h o / p a u / m i h u / k u h i / j i h a / s i h a / p o h o / p e h a / r o h i / r o h e / r o h o / r o h u / r o h a / r e h e / l e h o / j u h o / f u h i / d a i / g a h i / z o h o / b e h u / r i h e / s e h i / s e h a / v u h e / k i h a / x u / g e h e / b u h o ) &post-cmavo
VA <- &CMAVO ( v i / v a / v u ) &post-cmavo
VAU <- &CMAVO ( v a u ) &post-cmavo
VEI <- &CMAVO ( v e i ) &post-cmavo
VEhO <- &CMAVO ( v e h o ) &post-cmavo
VUhU <- &CMAVO ( g e h a / f u h u / p i h i / f e h i / v u h u / s u h i / j u h u / g e i / p a h i / f a h i / t e h a / c u h a / v a h a / n e h o / d e h o / f e h a / s a h o / r e h a / r i h o / s a h i / p i h a / s i h i ) &post-cmavo
VEhA <- &CMAVO ( v e h u / v e h a / v e h i / v e h e ) &post-cmavo
VIhA <- &CMAVO ( v i h i / v i h a / v i h u / v i h e ) &post-cmavo
VUhO <- &CMAVO ( v u h o ) &post-cmavo
XI <- &CMAVO ( x i ) &post-cmavo
Y <- &CMAVO ( y+ ) &post-cmavo
ZAhO <- &CMAVO ( c o h i / p u h o / c o h u / m o h u / c a h o / c o h a / d e h a / b a h o / d i h a / z a h o ) &post-cmavo
ZEhA <- &CMAVO ( z e h u / z e h a / z e h i / z e h e ) &post-cmavo
ZEI <- &CMAVO ( z e i ) &post-cmavo
ZI <- &CMAVO ( z u / z a / z i ) &post-cmavo
ZIhE <- &CMAVO ( z i h e ) &post-cmavo
ZO <- &CMAVO ( z o ) &post-cmavo
ZOI <- &CMAVO ( z o i / l a h o ) &post-cmavo
ZOhU <- &CMAVO ( z o h u ) &post-cmavo
;-----------------------
CMENE <- jbocme / naljbocme
naljbocme <- !h &consonant-final (vowel / consonant / digit)* &pause
jbocme <- !h &consonant-final (syllable / y-syllable / digit)* &pause
consonant-final <- (non-space &non-space)* consonant &pause
;-----------------------
CMAVO <- !cmene !CVCy-lujvo cmavo-form &post-cmavo
CVCy-lujvo <- C V C y h? initial-rafsi* (type-3 / fuhivla / gismu / end-rafsi)
cmavo-form <- consonant? glide? (nucleus h)* nucleus / y+ / digit
post-cmavo <- pause / !vowel lojban-word
;-----------------------
BRIVLA <- !cmavo !end-rafsi initial-rafsi* (type-3 / fuhivla / gismu / end-rafsi)
initial-rafsi <- brivla-rafsi / type-3-rafsi / fuhivla-rafsi / y-rafsi / !fuhivla !type-3 y-less-rafsi
brivla-rafsi <- !cmene !cmavo !slinkuhihy !h syllable syllable+ h y h?
slinkuhiy <- slinkuhi h y
;-----------------------
type-3 <- !cmene (C V C C / CC V C / C V C) (r / n / l) &C syllable+ &pause
type-3-rafsi <- !cmene (C V C C / CC V C / C V C) (r / n / l) &C syllable* y-syllable h?
;-----------------------
fuhivla <- !cmene !cmavo !rafsi-string !slinkuhi !h syllable syllable+ &pause
fuhivla-rafsi <- !cmene !cmavo !rafsi-string !slinkuhi !h syllable+ y-syllable h?
slinkuhi <- C rafsi-string
rafsi-string <- y-less-rafsi* (gismu / end-rafsi / y-rafsi / CC y)
;-----------------------
gismu <- (C V C C V / CC V C V) &pause
end-rafsi <- (C V h V / C VV / CC V) &pause
y-rafsi <- (C V C C / CC V C / C V C) y h?
y-less-rafsi <- (C V C !y / CC V / C VV R? / C V h V R?) !fuhivla !type-3 !brivla-rafsi !type-3-rafsi !fuhivla-rafsi
R <- r &consonant / n &r
CC <- &initial consonant consonant
C <- consonant
VV <- diphthong
V <- !y vowel
;-----------------------
y-syllable <- onset y coda?
syllable <- onset nucleus coda?
coda <- !syllable !y-syllable consonant
onset <- h / consonant? glide / initial
nucleus <- vowel / diphthong
initial <- (affricate / sibilant? middle? liquid?) &vowel
sibilant <- c / s !x / (j / z) !n !l !r
middle <- p / t !l / k / f / x / b / d !l / g / v / m / n !l !r
liquid <- l / r
;-----------------------
consonant <- voiced / unvoiced / l / m / n / r
affricate <- t c / t s / d j / d z
voiced <- b / d / g / j / v / z
unvoiced <- c / f / k / p / s / t / x
l <- comma* [l] !h !l
m <- comma* [m] !h !m !z
n <- comma* [n] !h !n !affricate
r <- comma* [r] !h !r
b <- comma* [b] !h !b !unvoiced
d <- comma* [d] !h !d !unvoiced
g <- comma* [g] !h !g !unvoiced
v <- comma* [v] !h !v !unvoiced
j <- comma* [j] !h !j !z !unvoiced
z <- comma* [z] !h !z !j !unvoiced
s <- comma* [s] !h !s !c !voiced
c <- comma* [c] !h !c !s !x !voiced
x <- comma* [x] !h !x !c !k !voiced
k <- comma* [k] !h !k !x !voiced
f <- comma* [f] !h !f !voiced
p <- comma* [p] !h !p !voiced
t <- comma* [t] !h !t !voiced
h <- comma* ['h] &vowel
;-------------------------
diphthong <- (a i / a u / e i / o i) !vowel !glide
glide <- (i / u) &vowel
vowel <- (a / e / i / o / u / y) !vowel
a <- comma* [a]
e <- comma* [e]
i <- comma* [i]
o <- comma* [o]
u <- comma* [u]
y <- comma* [y]
;-----------------------
digit <- comma* [0123456789] !h !vowel
pause <- comma* space-char+ / EOF
EOF <- comma* !.
SPACE dot-star <- .*
comma <- [,]
non-lojban-word <- !lojban-word non-space+
spaces <- !Y initial-spaces
initial-spaces <- (comma* space-char / !ybu Y)+ EOF? / EOF
NORATS non-space <- !space-char .
NORATS space-char <- [.\t\n\r?!\u0020]