camxes-beta.peg

# camxes.js.peg
# Copyright (c) 2013, 2014 Masato Hagiwara
# https://github.com/mhagiwara/camxes.js
#
# camxes.js can be used, modified, and re-distributed under MIT license.
# See LICENSE for the details.

# This is a Parsing Expression Grammar for Lojban.
# See http://bford.info/packrat/
#
# All rules have the form:
#
#     name = peg_expression
#
# which means that the grammatical construct "name" is parsed using
# "peg_expression".
#
# 1)  Names in lower case are grammatical constructs.
# 2)  Names in UPPER CASE are selma'o (lexeme) names, and are terminals.
# 3)  Concatenation is expressed by juxtaposition with no operator symbol.
# 4)  / represents *ORDERED* alternation (choice).  If the first
#     option succeeds, the others will never be checked.
# 5)  ? indicates that the element to the left is optional.
# 6)  * represents optional repetition of the construct to the left.
# 7)  + represents one_or_more repetition of the construct to the left.
# 8)  () serves to indicate the grouping of the other operators.
#
# Longest match wins.

# How to compile using Node.js: (Added by Masato Hagiwara)

# // load peg.js and the file system module
# > var PEG = require("pegjs")
# > var fs = require("fs")
# // read peg and build a parser
# > var camxes_peg = fs.readFileSync("/path/to/camxes.js.peg").toString();
# > var camxes = PEG.buildParser(camxes_peg, {cache: true});
# // test it
# > camxes.parse("ko'a broda");
# [ 'text',
#   [ 'text_1',
#     [ 'paragraphs', [Object] ] ] ]
# // write to a file
# > fs.writeFileSync("/path/to/camxes.js", camxes.toSource());


# ___ GRAMMAR ___



text <- intro_null NAI_clause* text_part_2 (!gek joik_jek)? text_1? faho_clause EOF?

intro_null <- initial_spaces? su_clause* intro_si_clause

text_part_2 <- (CMEVLA_clause+ / indicators?) free*

#; intro_sa_clause = SA_clause+ / any_word_SA_handling !(ZEI_clause SA_clause) intro_sa_clause
intro_si_clause <- si_clause? SI_clause*
faho_clause <- (FAhO_clause dot_star)?

# Please note that the "text_1" item in the text_1 production does
# *not* match the BNF. This is due to a bug in the BNF.  The change
# here was made to match grammar.300
text_1 <- I_clause (jek / joik)? (stag? BO_clause)? free* text_1? / NIhO_clause+ free* su_clause* paragraphs? / paragraphs

paragraphs <- paragraph? (NIhO_clause+ free* su_clause* paragraphs)?

paragraph <- (statement / fragment) (I_clause !jek !joik !joik_jek free* (statement / fragment)?)*

# BEGIN BETA: IAU
statement <- statement_0 IAU_elidible free* terms?

statement_0 <- statement_1 / prenex statement
# END BETA: IAU

statement_1 <- statement_2 (I_clause joik_jek statement_2?)*

statement_2 <- statement_3 (I_clause (jek / joik)? stag? BO_clause free* statement_2?)?

statement_3 <- sentence / tag? TUhE_clause free* text_1 TUhU_elidible free*

# BETA: NA sequence fragments
fragment <- prenex / terms VAU_elidible free* / ek free* / gihek free* / quantifier / (NA_clause !JA_clause free*)+ / relative_clauses / links / linkargs

prenex <- terms ZOhU_clause free*

#; sentence = (terms CU_clause? free*)? bridi_tail / bridi_tail

# BETA: JACU, JE.I
sentence <- terms? bridi_tail_t1 (joik_jek bridi_tail / joik_jek stag? KE_clause free* bridi_tail KEhE_elidible free*)* (joik_jek I_clause free* subsentence)*
# sentence = expr:(((terms bridi_tail_sa*)? CU_elidible free*)? bridi_tail_sa* bridi_tail) {return _node("sentence", expr);}

# BETA: JACU
bridi_tail_t1 <- bridi_tail_t2 (joik_jek stag? KE_clause free* bridi_tail KEhE_elidible free*)?

# BETA: JACU
bridi_tail_t2 <- bridi_tail (joik_jek stag? BO_clause free* bridi_tail)?


sentence_sa <- sentence_start (!sentence_start (sa_word / SA_clause !sentence_start ) )* SA_clause &text_1

sentence_start <- I_pre / NIhO_pre

subsentence <- sentence / prenex subsentence

# BETA: JACU
bridi_tail <- bridi_tail_1 ((gihek / joik_jek) stag? KE_clause free* bridi_tail KEhE_elidible free* tail_terms)?

bridi_tail_sa <- bridi_tail_start (term / !bridi_tail_start (sa_word / SA_clause !bridi_tail_start ) )* SA_clause &bridi_tail

bridi_tail_start <- ME_clause / NUhA_clause / NU_clause / NA_clause !KU_clause / NAhE_clause !BO_clause / selbri / tag bridi_tail_start / KE_clause bridi_tail_start / bridi_tail

# BETA: JACU
bridi_tail_1 <- bridi_tail_2 ((gihek / joik_jek) !(stag? BO_clause) !(stag? KE_clause) free* bridi_tail_2 tail_terms)*  #: LR2

# BETA: JACU
bridi_tail_2 <- CU_elidible free* bridi_tail_3 ((gihek / joik_jek) stag? BO_clause free* bridi_tail_2 tail_terms)?

# BETA: JACU
bridi_tail_3 <- (terms CU_elidible)* selbri tail_terms / gek_sentence

gek_sentence <- gek subsentence gik subsentence tail_terms / tag* KE_clause free* gek_sentence KEhE_elidible free* / NA_clause free* gek_sentence

tail_terms <- terms? VAU_elidible free*

terms <- terms_1+

#; terms_1 = terms_2 (PEhE_clause free* joik_jek terms_2)*

#; terms_2 = term (CEhE_clause free* term)*

terms_1 <- terms_2 (pehe_sa* PEhE_clause free* joik_jek terms_2)*

terms_2 <- term (cehe_sa* CEhE_clause free* nonabs_term)*

pehe_sa <- PEhE_clause (!PEhE_clause (sa_word / SA_clause !PEhE_clause))* SA_clause

cehe_sa <- CEhE_clause (!CEhE_clause (sa_word / SA_clause !CEhE_clause))* SA_clause

#;term = sumti / ( !gek (tag / FA_clause free*) (sumti / KU_elidible free*) ) / termset / NA_clause KU_clause free*

term <- term_sa* term_1

# BEGIN BETA: TERM JA TERM
term_1 <- term_2 (joik_ek !tag_bo_ke_bridi_tail term_2)*

tag_bo_ke_bridi_tail <- stag (BO_clause / KE_clause) CU_elidible free* (selbri / gek_sentence)

term_2 <- term_3 (joik_ek? stag? BO_clause term_3)*

term_3 <- sumti / tag_term / nontag_adverbial / termset

tag_term <- !gek (tag !(!tag selbri) / FA_clause free*) (sumti / KU_elidible free*)

nonabs_term <- term_sa* nonabs_term_1

nonabs_term_1 <- nonabs_term_2 (joik_ek !tag_bo_ke_bridi_tail term_2)*

nonabs_term_2 <- nonabs_term_3 (joik_ek? stag? BO_clause term_3)*

nonabs_term_3 <- sumti / nonabs_tag_term / nontag_adverbial / termset

nonabs_tag_term <- !gek (tag !(!tag selbri) / FA_clause free*) (sumti / KU_elidible free*)

# BETA: NOIhA, New-SOI
nontag_adverbial <- NA_clause free* KU_clause free* / NOIhA_clause free* sumti_tail SEhU_elidible free* / SOI_clause free* subsentence SEhU_elidible free*
# END BETA: TERM JA TERM

term_sa <- term_start (!term_start (sa_word / SA_clause !term_start ) )* SA_clause &term_1

term_start <- term_1 / LA_clause / LE_clause / LI_clause / LU_clause / LAhE_clause / quantifier term_start / gek sumti gik / FA_clause / tag term_start

# BETA: KE-termset
termset <- gek_termset / NUhI_clause free* gek terms NUhU_elidible free* gik terms NUhU_elidible free* / NUhI_clause free* terms NUhU_elidible free* / KE_clause terms KEhE_elidible

gek_termset <- gek terms_gik_terms

terms_gik_terms <- nonabs_term (gik / terms_gik_terms) nonabs_term

# BETA: Enhanced VUhO
sumti <- sumti_1 (VUhO_clause free* (relative_clauses (joik_ek sumti)?)?)?

sumti_1 <- sumti_2 (joik_ek stag? KE_clause free* sumti KEhE_elidible free*)?

sumti_2 <- sumti_3 (joik_ek sumti_3)*  #: LR2

sumti_3 <- sumti_4 (joik_ek stag? BO_clause free* sumti_3)?

sumti_4 <- sumti_5 / gek sumti gik sumti_4

sumti_5 <- quantifier? sumti_6 relative_clauses? / quantifier selbri KU_elidible free* relative_clauses?

# BETA: NAhE+SUMTI, LAhE+TERM, ZOhOI, LOhOI
sumti_6 <- ZO_clause free* / ZOI_clause free* / ZOhOI_clause free* / LOhU_clause free* / lerfu_string !MOI_clause BOI_elidible free* / LU_clause text LIhU_elidible free* / (LAhE_clause free* / NAhE_clause BO_clause? free*) (relative_clauses? sumti / term) LUhU_elidible free* / KOhA_clause free* / LA_clause free* relative_clauses? CMEVLA_clause+ free* / (LA_clause / LE_clause) free* sumti_tail KU_elidible free* / li_clause / LOhOI_clause free* subsentence KUhAU_clause free*

li_clause <- LI_clause free* mex LOhO_elidible free*

sumti_tail <- (sumti_6 relative_clauses?)? sumti_tail_1 / relative_clauses sumti_tail_1

sumti_tail_1 <- selbri relative_clauses? / quantifier selbri relative_clauses? / quantifier sumti

# BETA: JAPOI
relative_clauses <- relative_clause ((ZIhE_clause / joik_jek) free* relative_clause)* / gek relative_clauses gik relative_clauses

#; relative_clause = GOI_clause free* term GEhU_clause? free* / NOI_clause free* subsentence KUhO_clause? free*

relative_clause <- relative_clause_sa* relative_clause_1

relative_clause_sa <- relative_clause_start (!relative_clause_start (sa_word / SA_clause !relative_clause_start ) )* SA_clause &relative_clause_1

relative_clause_1 <- GOI_clause free* nonabs_term GEhU_elidible free* / NOI_clause free* subsentence KUhO_elidible free*

relative_clause_start <- GOI_clause / NOI_clause

selbri <- tag? selbri_1

selbri_1 <- selbri_2 / NA_clause free* selbri

selbri_2 <- selbri_3 (CO_clause free* selbri_2)?

selbri_3 <- selbri_4+  #: LR

selbri_4 <- selbri_5 (joik_jek selbri_5 / joik stag? KE_clause free* selbri_3 KEhE_elidible free*)*  #: LR2

selbri_5 <- selbri_6 ((jek / joik) stag? BO_clause free* selbri_5)?

selbri_6 <- tanru_unit (BO_clause free* selbri_6)? / NAhE_clause? free* guhek selbri gik selbri_6

tanru_unit <- tanru_unit_1 (CEI_clause free* tanru_unit_1)*

tanru_unit_1 <- tanru_unit_2 linkargs?

# ** zei is part of BRIVLA_clause

# BETA: Bare MEX, NUhA+opeator, GOhOI, MEhOI
tanru_unit_2 <- BRIVLA_clause free* / GOhA_clause RAhO_clause? free* / KE_clause free* selbri_3 KEhE_elidible free* / ME_clause free* (sumti / lerfu_string) MEhU_elidible free* MOI_clause? free* / mex MOI_clause free* / NUhA_clause free* operator / SE_clause free* tanru_unit_2 / JAI_clause free* tag? tanru_unit_2 / NAhE_clause free* tanru_unit_2 / NU_clause NAI_clause? free* (joik_jek NU_clause NAI_clause? free*)* subsentence KEI_elidible free* / GOhOI_clause free* / MEhOI_clause free*

#; linkargs = BE_clause free* term links? BEhO_clause? free*

linkargs <- linkargs_sa* linkargs_1

linkargs_1 <- BE_clause free* nonabs_term links? BEhO_elidible free*

linkargs_sa <- linkargs_start (!linkargs_start (sa_word / SA_clause !linkargs_start ) )* SA_clause &linkargs_1

linkargs_start <- BE_clause

#; links = BEI_clause free* term links?

links <- links_sa* links_1

links_1 <- BEI_clause free* nonabs_term links?

links_sa <- links_start (!links_start (sa_word / SA_clause !links_start ) )* SA_clause &links_1

links_start <- BEI_clause

# BEGIN BETA: MEX simplification
quantifier <- !selbri !sumti_6 mex

#;mex = mex_1 (operator mex_1)* / rp_clause

mex <- mex_1 (operator mex_1)*

mex_1 <- mex_2 (operator stag? BO_clause free* mex_1)?

mex_2 <- number BOI_elidible free* / lerfu_string BOI_elidible free* / VEI_clause free* mex VEhO_elidible free* / NIhE_clause free* selbri TEhU_elidible free* / MOhE_clause sumti TEhU_elidible free* / gek mex gik mex_2 / (LAhE_clause free* / NAhE_clause free* BO_clause? free*) mex LUhU_elidible free* / PEhO_clause free* operator mex+ KUhE_elidible free* / FUhA_clause rp_expression

rp_expression <- mex_1 (rp_expression operator)*

# END BETA: MEX simplification

#; operator = operator_1 (joik_jek operator_1 / joik stag? KE_clause free* operator KEhE_clause? free*)*

operator <- operator_sa* operator_0

operator_0 <- operator_1 (joik_jek operator_1 / joik stag? KE_clause free* operator KEhE_elidible free*)*

operator_sa <- operator_start (!operator_start (sa_word / SA_clause !operator_start) )* SA_clause &operator_0

operator_start <- guhek / KE_clause / SE_clause? NAhE_clause / SE_clause? MAhO_clause / SE_clause? VUhU_clause

# BETA: MEX simplification
operator_1 <- guhek operator_1 gik operator_2 / operator_2 (jek / joik) stag? BO_clause free* operator_1 / operator_2

operator_2 <- mex_operator / KE_clause free* operator KEhE_elidible free*

# BETA: MEX simplification
mex_operator <- SE_clause free* mex_operator / NAhE_clause free* mex_operator / MAhO_clause free* mex TEhU_elidible free* / NAhU_clause free* selbri TEhU_elidible free* / VUhU_clause free* / joik_jek free* / ek free*

#; operand = operand_1 (joik_ek stag? KE_clause free* operand KEhE_clause? free*)?

operand <- operand_sa* operand_0

operand_0 <- operand_1 (joik_ek stag? KE_clause free* operand KEhE_elidible free*)?

operand_sa <- operand_start (!operand_start (sa_word / SA_clause !operand_start) )* SA_clause &operand_0

operand_start <- quantifier / lerfu_word / NIhE_clause / MOhE_clause / JOhI_clause / gek / LAhE_clause / NAhE_clause

operand_1 <- operand_2 (joik_ek operand_2)*

operand_2 <- operand_3 (joik_ek stag? BO_clause free* operand_2)?

# BETA: NAhE+SUMTI
operand_3 <- quantifier / lerfu_string !MOI_clause BOI_elidible free* / NIhE_clause free* selbri TEhU_elidible free* / MOhE_clause free* sumti TEhU_elidible free* / JOhI_clause free* mex_2+ TEhU_elidible free* / gek operand gik operand_3 / (LAhE_clause free* / NAhE_clause BO_clause? free*) operand LUhU_elidible free*

# BETA: MEX simplification
# FIXME: forethought mex not possible anymore without pe'o. BIhE_clause isn't referenced anymore.
number <- (PA_clause / (NIhE_clause free* selbri TEhU_elidible free*) / (MOhE_clause free* sumti TEhU_elidible free*)) (PA_clause / (NIhE_clause free* selbri TEhU_elidible free*) / (MOhE_clause free* sumti TEhU_elidible free*))*

lerfu_string <- lerfu_word (PA_clause / lerfu_word)*

# ** BU clauses are part of BY_clause
lerfu_word <- BY_clause / LAU_clause lerfu_word / TEI_clause lerfu_string FOI_clause

ek <- NA_clause? SE_clause? A_clause NAI_clause?

#; gihek = NA_clause? SE_clause? GIhA_clause NAI_clause?
gihek <- gihek_sa* gihek_1

gihek_1 <- NA_clause? SE_clause? GIhA_clause NAI_clause?

gihek_sa <- gihek_1 (!gihek_1 (sa_word / SA_clause !gihek_1 ) )* SA_clause &gihek

# BETA: NAhU included in jek
jek <- NA_clause? SE_clause? (JA_clause / NAhU_clause free* selbri TEhU_elidible free*) NAI_clause?

joik <- SE_clause? JOI_clause NAI_clause? / interval / GAhO_clause interval GAhO_clause

interval <- SE_clause? BIhI_clause NAI_clause?

#; joik_ek = joik free* / ek free*
joik_ek <- joik_ek_sa* joik_ek_1

# BETA: A/JA/JOI/VUhU Merger
joik_ek_1 <- joik_jek

joik_ek_sa <- joik_ek_1 (!joik_ek_1 (sa_word / SA_clause !joik_ek_1 ) )* SA_clause &joik_ek

# BETA: A/JA/JOI/VUhU Merger
joik_jek <- joik free* / ek free* / jek free* / VUhU_clause free*

# BETA: gaJA
gek <- gak SE_clause? joik_jek / SE_clause? GA_clause free* / joik GI_clause free* / stag gik

# BETA: gaJA
gak <- ga_clause !gek free*

# BETA: guJA
guhek <- guk SE_clause? joik_jek / SE_clause? GUhA_clause NAI_clause? free*

# BETA: guJA
guk <- gu_clause !gek free*

gik <- GI_clause NAI_clause? free*

tag <- tense_modal (joik_jek tense_modal)*

#stag = simple_tense_modal ((jek / joik) simple_tense_modal)*

# BETA: Tag simplification
stag <- tense_modal (joik_jek tense_modal)*

# BETA: Tag simplification (dependency: NAI ∈ indicator)
# FIXME: Cannot use bare MEX with ROI.
tense_modal <- ((NAhE_clause? SE_clause? (BAI_clause / CAhA_clause / CUhE_clause / KI_clause / ZI_clause / PU_clause / VA_clause / MOhI_clause? FAhA_clause / ZEhA_clause / VEhA_clause / VIhA_clause / FEhE_clause? (VEI_clause free* mex VEhO_elidible free* / number) ROI_clause / FEhE_clause? TAhE_clause / FEhE_clause? ZAhO_clause / FIhO_clause free* selbri FEhU_elidible free* / FA_clause) free*)+)

# BETA: Bare MEX, LOhAI, Removal of Old-SOI
free <- SEI_clause free* (terms CU_elidible free*)? selbri SEhU_elidible / vocative relative_clauses? selbri relative_clauses? DOhU_elidible / vocative relative_clauses? CMEVLA_clause+ free* relative_clauses? DOhU_elidible / vocative sumti? DOhU_elidible / mex_2 MAI_clause free* / TO_clause text TOI_elidible / xi_clause / LOhAI_clause

# BETA: Bare MEX
xi_clause <- XI_clause free* mex_2 / XI_clause free* VEI_clause free* mex VEhO_elidible

vocative <- (COI_clause NAI_clause?)+ DOI_clause / (COI_clause NAI_clause?) (COI_clause NAI_clause?)* / DOI_clause

indicators <- FUhE_clause? indicator+

# BETA: NAI ∈ indicator
indicator <- ((UI_clause / CAI_clause) NAI_clause? / NAI_clause / DAhO_clause / FUhO_clause) !BU_clause


# ****************
# Magic Words
# ****************

zei_clause <- pre_clause zei_clause_no_pre
zei_clause_no_pre <- pre_zei_bu (zei_tail? BU_clause+)* zei_tail post_clause  #: LR
# zei_clause_no_SA = pre_zei_bu_no_SA (zei_tail? bu_tail)* zei_tail

bu_clause <- pre_clause bu_clause_no_pre
bu_clause_no_pre <- pre_zei_bu (BU_clause* zei_tail)* BU_clause+ post_clause  #: LR
# bu_clause_no_SA = pre_zei_bu_no_SA (bu_tail? zei_tail)* bu_tail

zei_tail <- (ZEI_clause any_word)+
bu_tail <- BU_clause+ # Obsolete: please use BU_clause+ instead for allowing later left-grouping faking.

pre_zei_bu <- !ZOI_start !BU_clause !ZEI_clause !SI_clause !SA_clause !SU_clause !FAhO_clause any_word_SA_handling si_clause?
# LOhU_pre / ZO_pre / ZOI_pre / !ZEI_clause !BU_clause !FAhO_clause !SI_clause !SA_clause !SU_clause any_word_SA_handling si_clause?
# pre_zei_bu_no_SA = LOhU_pre / ZO_pre / ZOI_pre / !ZEI_clause !BU_clause !FAhO_clause !SI_clause !SA_clause !SU_clause any_word si_clause?

dot_star <- .*  #: LEAF

# __ General Morphology Issues
#
# 1.  Spaces (including '.y') and UI are eaten *after* a word.
#
# 3.  BAhE is eaten *before* a word.

# Handling of what can go after a cmavo
post_clause <- spaces? si_clause? !ZEI_clause !BU_clause indicators*

pre_clause <- BAhE_clause*  #: LR

#any_word_SA_handling = BRIVLA_pre / known_cmavo_SA / !known_cmavo_pre CMAVO_pre / CMEVLA_pre
any_word_SA_handling <- BRIVLA_pre / known_cmavo_SA / CMAVO_pre / CMEVLA_pre

known_cmavo_SA <- A_pre / BAI_pre / BAhE_pre / BE_pre / BEI_pre / BEhO_pre / BIhE_pre / BIhI_pre / BO_pre / BOI_pre / BU_pre / BY_pre / CAI_pre / CAhA_pre / CEI_pre / CEhE_pre / CO_pre / COI_pre / CU_pre / CUhE_pre / DAhO_pre / DOI_pre / DOhU_pre / FA_pre / FAhA_pre / FEhE_pre / FEhU_pre / FIhO_pre / FOI_pre / FUhA_pre / FUhE_pre / FUhO_pre / GA_pre / GAhO_pre / GEhU_pre / GI_pre / GIhA_pre / GOI_pre / GOhA_pre / GUhA_pre / I_pre / JA_pre / JAI_pre / JOI_pre / JOhI_pre / KE_pre / KEI_pre / KEhE_pre / KI_pre / KOhA_pre / KU_pre / KUhE_pre / KUhO_pre / LA_pre / LAU_pre / LAhE_pre / LE_pre / LEhU_pre / LI_pre / LIhU_pre / LOhO_pre / LOhU_pre / LU_pre / LUhU_pre / MAI_pre / MAhO_pre / ME_pre / MEhU_pre / MOI_pre / MOhE_pre / MOhI_pre / NA_pre / NAI_pre / NAhE_pre / NAhU_pre / NIhE_pre / NIhO_pre / NOI_pre / NU_pre / NUhA_pre / NUhI_pre / NUhU_pre / PA_pre / PEhE_pre / PEhO_pre / PU_pre / RAhO_pre / ROI_pre / SA_pre / SE_pre / SEI_pre / SEhU_pre / SI_clause / SOI_pre / SU_pre / TAhE_pre / TEI_pre / TEhU_pre / TO_pre / TOI_pre / TUhE_pre / TUhU_pre / UI_pre / VA_pre / VAU_pre / VEI_pre / VEhA_pre / VEhO_pre / VIhA_pre / VUhO_pre / VUhU_pre / XI_pre / ZAhO_pre / ZEI_pre / ZEhA_pre / ZI_pre / ZIhE_pre / ZO_pre / ZOI_pre / ZOhU_pre

# Handling of spaces and things like spaces.
# ___ SPACE ___
# Do *NOT* delete the line above!

# SU clauses
su_clause <- (erasable_clause / su_word)* SU_clause

# Handling of SI and interactions with zo and lo'u...le'u

si_clause <- ((erasable_clause / si_word / SA_clause) si_clause? SI_clause)+

erasable_clause <- bu_clause_no_pre !ZEI_clause !BU_clause / zei_clause_no_pre !ZEI_clause !BU_clause

sa_word <- pre_zei_bu

si_word <- pre_zei_bu

su_word <- !ZOI_start !NIhO_clause !LU_clause !TUhE_clause !TO_clause !SU_clause !FAhO_clause any_word_SA_handling


# ___ ELIDIBLE TERMINATORS ___

# BETA: IAU
BEhO_elidible <- BEhO_clause?
BOI_elidible <- BOI_clause?
CU_elidible <- CU_clause?
DOhU_elidible <- DOhU_clause?
FEhU_elidible <- FEhU_clause?
# FOI and FUhO are never elidible
GEhU_elidible <- GEhU_clause?
IAU_elidible <- IAU_clause?
KEI_elidible <- KEI_clause?
KEhE_elidible <- KEhE_clause?
KU_elidible <- KU_clause?
KUhE_elidible <- KUhE_clause?
KUhO_elidible <- KUhO_clause?
# LEhU is never elidible
LIhU_elidible <- LIhU_clause?
LOhO_elidible <- LOhO_clause?
LUhU_elidible <- LUhU_clause?
MEhU_elidible <- MEhU_clause?
NUhU_elidible <- NUhU_clause?
SEhU_elidible <- SEhU_clause?
TEhU_elidible <- TEhU_clause?
TOI_elidible <- TOI_clause?
TUhU_elidible <- TUhU_clause?
VAU_elidible <- VAU_clause?
VEhO_elidible <- VEhO_clause?


# ___ SELMAHO ___
# Do *NOT* delete the line above!

BRIVLA_clause <- BRIVLA_pre BRIVLA_post / zei_clause
BRIVLA_pre <- pre_clause BRIVLA spaces?
BRIVLA_post <- post_clause
# BRIVLA_no_SA_handling = pre_clause BRIVLA post_clause / zei_clause_no_SA

CMEVLA_clause <- CMEVLA_pre CMEVLA_post
CMEVLA_pre <- pre_clause CMEVLA spaces?
CMEVLA_post <- post_clause
# CMEVLA_no_SA_handling = pre_clause CMEVLA post_clause

CMAVO_clause <- CMAVO_pre CMAVO_post
CMAVO_pre <- pre_clause CMAVO spaces?
CMAVO_post <- post_clause
# CMAVO_no_SA_handling = pre_clause CMAVO post_clause

#         eks; basic afterthought logical connectives
A_clause <- A_pre A_post
A_pre <- pre_clause A spaces?
A_post <- post_clause
# A_no_SA_handling = pre_clause A post_clause


#         modal operators
BAI_clause <- BAI_pre BAI_post
BAI_pre <- pre_clause BAI spaces?
BAI_post <- post_clause
# BAI_no_SA_handling = pre_clause BAI post_clause

#         next word intensifier
BAhE_clause <- BAhE_pre BAhE_post
BAhE_pre <- BAhE spaces?
BAhE_post <- si_clause? !ZEI_clause !BU_clause
# BAhE_no_SA_handling = BAhE spaces? BAhE_post

#         sumti link to attach sumti to a selbri
BE_clause <- BE_pre BE_post
BE_pre <- pre_clause BE spaces?
BE_post <- post_clause
# BE_no_SA_handling = pre_clause BE post_clause

#         multiple sumti separator between BE, BEI
BEI_clause <- BEI_pre BEI_post
BEI_pre <- pre_clause BEI spaces?
BEI_post <- post_clause
# BEI_no_SA_handling = pre_clause BEI post_clause

#         terminates BEBEI specified descriptors
BEhO_clause <- BEhO_pre BEhO_post
BEhO_pre <- pre_clause BEhO spaces?
BEhO_post <- post_clause
# BEhO_no_SA_handling = pre_clause BEhO post_clause

#         prefix for high_priority MEX operator
BIhE_clause <- BIhE_pre BIhE_post
BIhE_pre <- pre_clause BIhE spaces?
BIhE_post <- post_clause
# BIhE_no_SA_handling = pre_clause BIhE post_clause

#         interval component of JOI
BIhI_clause <- BIhI_pre BIhI_post
BIhI_pre <- pre_clause BIhI spaces?
BIhI_post <- post_clause
# BIhI_no_SA_handling = pre_clause BIhI post_clause

#         joins two units with shortest scope
BO_clause <- BO_pre BO_post
BO_pre <- pre_clause BO spaces?
BO_post <- post_clause
# BO_no_SA_handling = pre_clause BO post_clause

#         number or lerfu_string terminator
BOI_clause <- BOI_pre BOI_post
BOI_pre <- pre_clause BOI spaces?
BOI_post <- post_clause
# BOI_no_SA_handling = pre_clause BOI post_clause

#         turns any word into a BY lerfu word
BU_clause <- BU_pre BU_post
# BU_clause_no_SA = BU_pre_no_SA BU BU_post
BU_pre <- pre_clause BU spaces?
# BU_pre_no_SA = pre_clause
BU_post <- spaces?
# BU_no_SA_handling = pre_clause BU spaces?

#         individual lerfu words
BY_clause <- BY_pre BY_post / bu_clause
BY_pre <- pre_clause BY spaces?
BY_post <- post_clause
# BY_no_SA_handling = pre_clause BY post_clause / bu_clause_no_SA


#         specifies actualitypotentiality of tense
CAhA_clause <- CAhA_pre CAhA_post
CAhA_pre <- pre_clause CAhA spaces?
CAhA_post <- post_clause
# CAhA_no_SA_handling = pre_clause CAhA post_clause

#         afterthought intensity marker
CAI_clause <- CAI_pre CAI_post
CAI_pre <- pre_clause CAI spaces?
CAI_post <- post_clause
# CAI_no_SA_handling = pre_clause CAI post_clause

#         pro_bridi assignment operator
CEI_clause <- CEI_pre CEI_post
CEI_pre <- pre_clause CEI spaces?
CEI_post <- post_clause
# CEI_no_SA_handling = pre_clause CEI post_clause

#         afterthought term list connective
CEhE_clause <- CEhE_pre CEhE_post
CEhE_pre <- pre_clause CEhE spaces?
CEhE_post <- post_clause
# CEhE_no_SA_handling = pre_clause CEhE post_clause

#         names; require consonant end, then pause no

#                                    LA or DOI selma'o embedded, pause before if

#                                    vowel initial and preceded by a vowel

#         tanru inversion
CO_clause <- CO_pre CO_post
CO_pre <- pre_clause CO spaces?
CO_post <- post_clause
# CO_no_SA_handling = pre_clause CO post_clause

COI_clause <- COI_pre COI_post
COI_pre <- pre_clause COI spaces?
COI_post <- post_clause
# COI_no_SA_handling = pre_clause COI post_clause

#         vocative marker permitted inside names; must

#                                    always be followed by pause or DOI

#         separator between head sumti and selbri
CU_clause <- CU_pre CU_post
CU_pre <- pre_clause CU spaces?
CU_post <- post_clause
# CU_no_SA_handling = pre_clause CU post_clause

#         tensemodal question
CUhE_clause <- CUhE_pre CUhE_post
CUhE_pre <- pre_clause CUhE spaces?
CUhE_post <- post_clause
# CUhE_no_SA_handling = pre_clause CUhE post_clause


#         cancel anaphoracataphora assignments
DAhO_clause <- DAhO_pre DAhO_post
DAhO_pre <- pre_clause DAhO spaces?
DAhO_post <- post_clause
# DAhO_no_SA_handling = pre_clause DAhO post_clause

#         vocative marker
DOI_clause <- DOI_pre DOI_post
DOI_pre <- pre_clause DOI spaces?
DOI_post <- post_clause
# DOI_no_SA_handling = pre_clause DOI post_clause

#         terminator for DOI_marked vocatives
DOhU_clause <- DOhU_pre DOhU_post
DOhU_pre <- pre_clause DOhU spaces?
DOhU_post <- post_clause
# DOhU_no_SA_handling = pre_clause DOhU post_clause


#         modifier head generic case tag
FA_clause <- FA_pre FA_post
FA_pre <- pre_clause FA spaces?
FA_post <- post_clause
# FA_no_SA_handling = pre_clause FA post_clause

#         superdirections in space
FAhA_clause <- FAhA_pre FAhA_post
FAhA_pre <- pre_clause FAhA spaces?
FAhA_post <- post_clause
# FAhA_no_SA_handling = pre_clause FAhA post_clause


#         normally elided 'done pause' to indicate end
#                                    of utterance string

FAhO_clause <- pre_clause FAhO spaces?

#         space interval mod flag
FEhE_clause <- FEhE_pre FEhE_post
FEhE_pre <- pre_clause FEhE spaces?
FEhE_post <- post_clause
# FEhE_no_SA_handling = pre_clause FEhE post_clause

#         ends bridi to modal conversion
FEhU_clause <- FEhU_pre FEhU_post
FEhU_pre <- pre_clause FEhU spaces?
FEhU_post <- post_clause
# FEhU_no_SA_handling = pre_clause FEhU post_clause

#         marks bridi to modal conversion
FIhO_clause <- FIhO_pre FIhO_post
FIhO_pre <- pre_clause FIhO spaces?
FIhO_post <- post_clause
# FIhO_no_SA_handling = pre_clause FIhO post_clause

#         end compound lerfu
FOI_clause <- FOI_pre FOI_post
FOI_pre <- pre_clause FOI spaces?
FOI_post <- post_clause
# FOI_no_SA_handling = pre_clause FOI post_clause

#         reverse Polish flag
FUhA_clause <- FUhA_pre FUhA_post
FUhA_pre <- pre_clause FUhA spaces?
FUhA_post <- post_clause
# FUhA_no_SA_handling = pre_clause FUhA post_clause

#         open long scope for indicator
FUhE_clause <- FUhE_pre FUhE_post
FUhE_pre <- pre_clause FUhE spaces?
FUhE_post <- !BU_clause spaces? !ZEI_clause !BU_clause
# FUhE_no_SA_handling = pre_clause FUhE post_clause

#         close long scope for indicator
FUhO_clause <- FUhO_pre FUhO_post
FUhO_pre <- pre_clause FUhO spaces?
FUhO_post <- post_clause
# FUhO_no_SA_handling = pre_clause FUhO post_clause


#         geks; forethought logical connectives
GA_clause <- GA_pre GA_post
GA_pre <- pre_clause GA spaces?
GA_post <- post_clause
# GA_no_SA_handling = pre_clause GA post_clause

#         openclosed interval markers for BIhI
GAhO_clause <- GAhO_pre GAhO_post
GAhO_pre <- pre_clause GAhO spaces?
GAhO_post <- post_clause
# GAhO_no_SA_handling = pre_clause GAhO post_clause

#         marker ending GOI relative clauses
GEhU_clause <- GEhU_pre GEhU_post
GEhU_pre <- pre_clause GEhU spaces?
GEhU_post <- post_clause
# GEhU_no_SA_handling = pre_clause GEhU post_clause

#         forethought medial marker
GI_clause <- GI_pre GI_post
GI_pre <- pre_clause GI spaces?
GI_post <- post_clause
# GI_no_SA_handling = pre_clause GI post_clause

#         logical connectives for bridi_tails
GIhA_clause <- GIhA_pre GIhA_post
GIhA_pre <- pre_clause GIhA spaces?
GIhA_post <- post_clause
# GIhA_no_SA_handling = pre_clause GIhA post_clause

#         attaches a sumti modifier to a sumti
GOI_clause <- GOI_pre GOI_post
GOI_pre <- pre_clause GOI spaces?
GOI_post <- post_clause
# GOI_no_SA_handling = pre_clause GOI post_clause

#         pro_bridi
GOhA_clause <- GOhA_pre GOhA_post
GOhA_pre <- pre_clause GOhA spaces?
GOhA_post <- post_clause
# GOhA_no_SA_handling = pre_clause GOhA post_clause

#         GEK for tanru units, corresponds to JEKs
GUhA_clause <- GUhA_pre GUhA_post
GUhA_pre <- pre_clause GUhA spaces?
GUhA_post <- post_clause
# GUhA_no_SA_handling = pre_clause GUhA post_clause


#         sentence link
I_clause <- sentence_sa* I_pre I_post
I_pre <- pre_clause I spaces?
I_post <- post_clause
# I_no_SA_handling = pre_clause I post_clause


#         jeks; logical connectives within tanru
JA_clause <- JA_pre JA_post
JA_pre <- pre_clause JA spaces?
JA_post <- post_clause
# JA_no_SA_handling = pre_clause JA post_clause

#         modal conversion flag
JAI_clause <- JAI_pre JAI_post
JAI_pre <- pre_clause JAI spaces?
JAI_post <- post_clause
# JAI_no_SA_handling = pre_clause JAI post_clause

#         flags an array operand
JOhI_clause <- JOhI_pre JOhI_post
JOhI_pre <- pre_clause JOhI spaces?
JOhI_post <- post_clause
# JOhI_no_SA_handling = pre_clause JOhI post_clause

#         non_logical connectives
JOI_clause <- JOI_pre JOI_post
JOI_pre <- pre_clause JOI spaces?
JOI_post <- post_clause
# JOI_no_SA_handling = pre_clause JOI post_clause


#         left long scope marker
KE_clause <- KE_pre KE_post
KE_pre <- pre_clause KE spaces?
KE_post <- post_clause
# KE_no_SA_handling = pre_clause KE post_clause

#         right terminator for KE groups
KEhE_clause <- KEhE_pre KEhE_post
KEhE_pre <- pre_clause KEhE spaces?
KEhE_post <- post_clause
# KEhE_no_SA_handling = pre_clause KEhE post_clause

#         right terminator, NU abstractions
KEI_clause <- KEI_pre KEI_post
KEI_pre <- pre_clause KEI spaces?
KEI_post <- post_clause
KEI_no_SA_handling <- pre_clause KEI post_clause

#         multiple utterance scope for tenses
KI_clause <- KI_pre KI_post
KI_pre <- pre_clause KI spaces?
KI_post <- post_clause
# KI_no_SA_handling = pre_clause KI post_clause

#         sumti anaphora
KOhA_clause <- KOhA_pre KOhA_post
KOhA_pre <- pre_clause KOhA spaces?
KOhA_post <- post_clause
# KOhA_no_SA_handling = pre_clause KOhA spaces?

#         right terminator for descriptions, etc.
KU_clause <- KU_pre KU_post
KU_pre <- pre_clause KU spaces?
KU_post <- post_clause
# KU_no_SA_handling = pre_clause KU post_clause

#         MEX forethought delimiter
KUhE_clause <- KUhE_pre KUhE_post
KUhE_pre <- pre_clause KUhE spaces?
KUhE_post <- post_clause
# KUhE_no_SA_handling = pre_clause KUhE post_clause

#         right terminator, NOI relative clauses
KUhO_clause <- KUhO_pre KUhO_post
KUhO_pre <- pre_clause KUhO spaces?
KUhO_post <- post_clause
# KUhO_no_SA_handling = pre_clause KUhO post_clause


#         name descriptors
LA_clause <- LA_pre LA_post
LA_pre <- pre_clause LA spaces?
LA_post <- post_clause
# LA_no_SA_handling = pre_clause LA post_clause

#         lerfu prefixes
LAU_clause <- LAU_pre LAU_post
LAU_pre <- pre_clause LAU spaces?
LAU_post <- post_clause
# LAU_no_SA_handling = pre_clause LAU post_clause

#         sumti qualifiers
LAhE_clause <- LAhE_pre LAhE_post
LAhE_pre <- pre_clause LAhE spaces?
LAhE_post <- post_clause
# LAhE_no_SA_handling = pre_clause LAhE post_clause

#         sumti descriptors
LE_clause <- LE_pre LE_post
LE_pre <- pre_clause LE spaces?
LE_post <- post_clause
# LE_no_SA_handling = pre_clause LE post_clause


#         possibly ungrammatical text right quote
LEhU_clause <- LEhU_pre LEhU_post
LEhU_pre <- pre_clause LEhU spaces?
LEhU_post <- spaces?
# LEhU_clause_no_SA = LEhU_pre_no_SA LEhU_post
# LEhU_pre_no_SA = pre_clause LEhU spaces?
# LEhU_no_SA_handling = pre_clause LEhU post_clause

#         convert number to sumti
LI_clause <- LI_pre LI_post
LI_pre <- pre_clause LI spaces?
LI_post <- post_clause
# LI_no_SA_handling = pre_clause LI post_clause

#         grammatical text right quote
LIhU_clause <- LIhU_pre LIhU_post
LIhU_pre <- pre_clause LIhU spaces?
LIhU_post <- post_clause
# LIhU_no_SA_handling = pre_clause LIhU post_clause

#         elidable terminator for LI
LOhO_clause <- LOhO_pre LOhO_post
LOhO_pre <- pre_clause LOhO spaces?
LOhO_post <- post_clause
# LOhO_no_SA_handling = pre_clause LOhO post_clause

#         possibly ungrammatical text left quote
LOhU_clause <- LOhU_pre LOhU_post
LOhU_pre <- pre_clause LOhU spaces? (!LEhU any_word)* LEhU_clause spaces?
LOhU_post <- post_clause
# LOhU_no_SA_handling = pre_clause LOhU spaces? (!LEhU any_word)* LEhU_clause spaces?

#         grammatical text left quote
LU_clause <- LU_pre LU_post
LU_pre <- pre_clause LU spaces?
LU_post <- spaces? si_clause? !ZEI_clause !BU_clause
# LU_post isn't post_clause for avoiding indicators to attach to LU in the parse tree.
# LU_no_SA_handling = pre_clause LU post_clause

#         LAhE close delimiter
LUhU_clause <- LUhU_pre LUhU_post
LUhU_pre <- pre_clause LUhU spaces?
LUhU_post <- post_clause
# LUhU_no_SA_handling = pre_clause LUhU post_clause


#         change MEX expressions to MEX operators
MAhO_clause <- MAhO_pre MAhO_post
MAhO_pre <- pre_clause MAhO spaces?
MAhO_post <- post_clause
# MAhO_no_SA_handling = pre_clause MAhO post_clause

#         change numbers to utterance ordinals
MAI_clause <- MAI_pre MAI_post
MAI_pre <- pre_clause MAI spaces?
MAI_post <- post_clause
# MAI_no_SA_handling = pre_clause MAI post_clause

#         converts a sumti into a tanru_unit
ME_clause <- ME_pre ME_post
ME_pre <- pre_clause ME spaces?
ME_post <- post_clause
# ME_no_SA_handling = pre_clause ME post_clause

#         terminator for ME
MEhU_clause <- MEhU_pre MEhU_post
MEhU_pre <- pre_clause MEhU spaces?
MEhU_post <- post_clause
# MEhU_no_SA_handling = pre_clause MEhU post_clause

#         change sumti to operand, inverse of LI
MOhE_clause <- MOhE_pre MOhE_post
MOhE_pre <- pre_clause MOhE spaces?
MOhE_post <- post_clause
# MOhE_no_SA_handling = pre_clause MOhE post_clause

#         motion tense marker
MOhI_clause <- MOhI_pre MOhI_post
MOhI_pre <- pre_clause MOhI spaces?
MOhI_post <- post_clause
# MOhI_no_SA_handling = pre_clause MOhI post_clause

#         change number to selbri
MOI_clause <- MOI_pre MOI_post
MOI_pre <- pre_clause MOI spaces?
MOI_post <- post_clause
# MOI_no_SA_handling = pre_clause MOI post_clause


#         bridi negation
NA_clause <- NA_pre NA_post
NA_pre <- pre_clause NA spaces?
NA_post <- post_clause
# NA_no_SA_handling = pre_clause NA post_clause

#         attached to words to negate them
NAI_clause <- NAI_pre NAI_post
NAI_pre <- pre_clause NAI spaces?
NAI_post <- post_clause
# NAI_no_SA_handling = pre_clause NAI post_clause

#         scalar negation
NAhE_clause <- NAhE_pre NAhE_post
NAhE_pre <- pre_clause NAhE spaces?
NAhE_post <- post_clause
# NAhE_no_SA_handling = pre_clause NAhE post_clause

#         change a selbri into an operator
NAhU_clause <- NAhU_pre NAhU_post
NAhU_pre <- pre_clause NAhU spaces?
NAhU_post <- post_clause
# NAhU_no_SA_handling = pre_clause NAhU post_clause

#         change selbri to operand; inverse of MOI
NIhE_clause <- NIhE_pre NIhE_post
NIhE_pre <- pre_clause NIhE spaces?
NIhE_post <- post_clause
# NIhE_no_SA_handling = pre_clause NIhE post_clause

#         new paragraph; change of subject
NIhO_clause <- sentence_sa* NIhO_pre NIhO_post
NIhO_pre <- pre_clause NIhO spaces?
NIhO_post <- su_clause* post_clause
# NIhO_no_SA_handling = pre_clause NIhO su_clause* post_clause

#         attaches a subordinate clause to a sumti
NOI_clause <- NOI_pre NOI_post
NOI_pre <- pre_clause NOI spaces?
NOI_post <- post_clause
# NOI_no_SA_handling = pre_clause NOI post_clause

#         abstraction
NU_clause <- NU_pre NU_post
NU_pre <- pre_clause NU spaces?
NU_post <- post_clause
# NU_no_SA_handling = pre_clause NU post_clause

#         change operator to selbri; inverse of MOhE
NUhA_clause <- NUhA_pre NUhA_post
NUhA_pre <- pre_clause NUhA spaces?
NUhA_post <- post_clause
# NUhA_no_SA_handling = pre_clause NUhA post_clause

#         marks the start of a termset
NUhI_clause <- NUhI_pre NUhI_post
NUhI_pre <- pre_clause NUhI spaces?
NUhI_post <- post_clause
# NUhI_no_SA_handling = pre_clause NUhI post_clause

#         marks the middle and end of a termset
NUhU_clause <- NUhU_pre NUhU_post
NUhU_pre <- pre_clause NUhU spaces?
NUhU_post <- post_clause
# NUhU_no_SA_handling = pre_clause NUhU post_clause


#         numbers and numeric punctuation
PA_clause <- PA_pre PA_post
PA_pre <- pre_clause PA spaces?
PA_post <- post_clause
# PA_no_SA_handling = pre_clause PA post_clause

#         afterthought termset connective prefix
PEhE_clause <- PEhE_pre PEhE_post
PEhE_pre <- pre_clause PEhE spaces?
PEhE_post <- post_clause
# PEhE_no_SA_handling = pre_clause PEhE post_clause

#         forethought (Polish) flag
PEhO_clause <- PEhO_pre PEhO_post
PEhO_pre <- pre_clause PEhO spaces?
PEhO_post <- post_clause
# PEhO_no_SA_handling = pre_clause PEhO post_clause

#         directions in time
PU_clause <- PU_pre PU_post
PU_pre <- pre_clause PU spaces?
PU_post <- post_clause
# PU_no_SA_handling = pre_clause PU post_clause


#         flag for modified interpretation of GOhI
RAhO_clause <- RAhO_pre RAhO_post
RAhO_pre <- pre_clause RAhO spaces?
RAhO_post <- post_clause
# RAhO_no_SA_handling = pre_clause RAhO post_clause

#         converts number to extensional tense
ROI_clause <- ROI_pre ROI_post
ROI_pre <- pre_clause ROI spaces?
ROI_post <- post_clause
# ROI_no_SA_handling = pre_clause ROI post_clause

SA_clause <- SA_pre SA_post
SA_pre <- pre_clause SA spaces?
SA_post <- spaces?

#         metalinguistic eraser to the beginning of

#                                    the current utterance

#         conversions
SE_clause <- SE_pre SE_post
SE_pre <- pre_clause SE spaces?
SE_post <- post_clause
# SE_no_SA_handling = pre_clause SE post_clause

#         metalinguistic bridi insert marker
SEI_clause <- SEI_pre SEI_post
SEI_pre <- pre_clause SEI spaces?
SEI_post <- post_clause
# SEI_no_SA_handling = pre_clause SEI post_clause

#         metalinguistic bridi end marker
SEhU_clause <- SEhU_pre SEhU_post
SEhU_pre <- pre_clause SEhU spaces?
SEhU_post <- post_clause
# SEhU_no_SA_handling = pre_clause SEhU post_clause

#         metalinguistic single word eraser
SI_clause <- spaces? SI spaces?

# BETA: bridi relative clause
SOI_clause <- SOI_pre SOI_post
SOI_pre <- pre_clause SOI spaces?
SOI_post <- post_clause
# SOI_no_SA_handling = pre_clause SOI post_clause

#         metalinguistic eraser of the entire text
SU_clause <- SU_pre SU_post
SU_pre <- pre_clause SU spaces?
SU_post <- post_clause


#         tense interval properties
TAhE_clause <- TAhE_pre TAhE_post
TAhE_pre <- pre_clause TAhE spaces?
TAhE_post <- post_clause
# TAhE_no_SA_handling = pre_clause TAhE post_clause

#         closing gap for MEX constructs
TEhU_clause <- TEhU_pre TEhU_post
TEhU_pre <- pre_clause TEhU spaces?
TEhU_post <- post_clause
# TEhU_no_SA_handling = pre_clause TEhU post_clause

#         start compound lerfu
TEI_clause <- TEI_pre TEI_post
TEI_pre <- pre_clause TEI spaces?
TEI_post <- post_clause
# TEI_no_SA_handling = pre_clause TEI post_clause

#         left discursive parenthesis
TO_clause <- TO_pre TO_post
TO_pre <- pre_clause TO spaces?
TO_post <- post_clause
# TO_no_SA_handling = pre_clause TO post_clause

#         right discursive parenthesis
TOI_clause <- TOI_pre TOI_post
TOI_pre <- pre_clause TOI spaces?
TOI_post <- post_clause
# TOI_no_SA_handling = pre_clause TOI post_clause

#         multiple utterance scope mark
TUhE_clause <- TUhE_pre TUhE_post
TUhE_pre <- pre_clause TUhE spaces?
TUhE_post <- su_clause* post_clause
# TUhE_no_SA_handling = pre_clause TUhE su_clause* post_clause

#         multiple utterance end scope mark
TUhU_clause <- TUhU_pre TUhU_post
TUhU_pre <- pre_clause TUhU spaces?
TUhU_post <- post_clause
# TUhU_no_SA_handling = pre_clause TUhU post_clause


#         attitudinals, observationals, discursives
UI_clause <- UI_pre UI_post
UI_pre <- pre_clause UI spaces?
UI_post <- post_clause
# UI_no_SA_handling = pre_clause UI post_clause


#         distance in space_time
VA_clause <- VA_pre VA_post
VA_pre <- pre_clause VA spaces?
VA_post <- post_clause
# VA_no_SA_handling = pre_clause VA post_clause

#         end simple bridi or bridi_tail
VAU_clause <- VAU_pre VAU_post
VAU_pre <- pre_clause VAU spaces?
VAU_post <- post_clause
# VAU_no_SA_handling = pre_clause VAU post_clause

#         left MEX bracket
VEI_clause <- VEI_pre VEI_post
VEI_pre <- pre_clause VEI spaces?
VEI_post <- post_clause
# VEI_no_SA_handling = pre_clause VEI post_clause

#         right MEX bracket
VEhO_clause <- VEhO_pre VEhO_post
VEhO_pre <- pre_clause VEhO spaces?
VEhO_post <- post_clause
# VEhO_no_SA_handling = pre_clause VEhO post_clause

#         MEX operator
VUhU_clause <- VUhU_pre VUhU_post
VUhU_pre <- pre_clause VUhU spaces?
VUhU_post <- post_clause
# VUhU_no_SA_handling = pre_clause VUhU post_clause

#         space_time interval size
VEhA_clause <- VEhA_pre VEhA_post
VEhA_pre <- pre_clause VEhA spaces?
VEhA_post <- post_clause
# VEhA_no_SA_handling = pre_clause VEhA post_clause

#         space_time dimensionality marker
VIhA_clause <- VIhA_pre VIhA_post
VIhA_pre <- pre_clause VIhA spaces?
VIhA_post <- post_clause
# VIhA_no_SA_handling = pre_clause VIhA post_clause

VUhO_clause <- VUhO_pre VUhO_post
VUhO_pre <- pre_clause VUhO spaces?
VUhO_post <- post_clause
# VUhO_no_SA_handling = pre_clause VUhO post_clause

# glue between logically connected sumti and relative clauses


#         subscripting operator
XI_clause <- XI_pre XI_post
XI_pre <- pre_clause XI spaces?
XI_post <- post_clause
# XI_no_SA_handling = pre_clause XI post_clause


#         hesitation
# Very very special case.  Handled in the morphology section.
# Y_clause = spaces? Y spaces?


#         event properties _ inchoative, etc.
ZAhO_clause <- ZAhO_pre ZAhO_post
ZAhO_pre <- pre_clause ZAhO spaces?
ZAhO_post <- post_clause
# ZAhO_no_SA_handling = pre_clause ZAhO post_clause

#         time interval size tense
ZEhA_clause <- ZEhA_pre ZEhA_post
ZEhA_pre <- pre_clause ZEhA spaces?
ZEhA_post <- post_clause
# ZEhA_no_SA_handling = pre_clause ZEhA post_clause

#         lujvo glue
ZEI_clause <- ZEI_pre ZEI_post
# ZEI_clause_no_SA = ZEI_pre_no_SA ZEI ZEI_post
ZEI_pre <- pre_clause ZEI spaces?
# ZEI_pre_no_SA = pre_clause
ZEI_post <- spaces?
# ZEI_no_SA_handling = pre_clause ZEI post_clause

#         time distance tense
ZI_clause <- ZI_pre ZI_post
ZI_pre <- pre_clause ZI spaces?
ZI_post <- post_clause
# ZI_no_SA_handling = pre_clause ZI post_clause

#         conjoins relative clauses
ZIhE_clause <- ZIhE_pre ZIhE_post
ZIhE_pre <- pre_clause ZIhE spaces?
ZIhE_post <- post_clause
# ZIhE_no_SA_handling = pre_clause ZIhE post_clause

#         single word metalinguistic quote marker
ZO_clause <- ZO_pre ZO_post
ZO_pre <- pre_clause ZO spaces? any_word spaces?
ZO_post <- post_clause
# ZO_no_SA_handling = pre_clause ZO spaces? any_word spaces?

#         delimited quote marker
ZOI_clause <- ZOI_pre ZOI_post
ZOI_pre <- pre_clause ZOI spaces? zoi_open spaces? (zoi_word spaces)* zoi_close spaces?
ZOI_post <- post_clause
ZOI_start <- !ZOI_pre ZOI
# ZOI_no_SA_handling = pre_clause ZOI spaces? zoi_open zoi_word* zoi_close spaces?

#         prenex terminator (not elidable)
ZOhU_clause <- ZOhU_pre ZOhU_post
ZOhU_pre <- pre_clause ZOhU spaces?
ZOhU_post <- post_clause
# ZOhU_no_SA_handling = pre_clause ZOhU post_clause

# BEGIN BETA: gaJA, guJA
ga_clause <- ga_pre ga_post
ga_pre <- pre_clause ga_word spaces?
ga_post <- post_clause
ga_word <- &cmavo ( g a ) &post_word

gu_clause <- gu_pre gu_post
gu_pre <- pre_clause gu_word spaces?
gu_post <- post_clause
gu_word <- &cmavo ( g u ) &post_word
# END BETA: gaJA, guJA

# BEGIN BETA: Experimental selmaho

GOhOI_clause <- GOhOI_pre GOhOI_post
GOhOI_pre <- pre_clause GOhOI spaces? any_word spaces?
GOhOI_post <- post_clause

IAU_clause <- IAU_pre IAU_post
IAU_pre <- pre_clause IAU spaces?
IAU_post <- post_clause

# BETA: Attempt to formalize lo'ai..sa'ai..le'ai replacement expressions.
#       Possibly ungrammatical replacement expressions.
LOhAI_clause <- LOhAI_pre LOhAI_post
LOhAI_pre <- pre_clause (LOhAI spaces? (!LOhAI !LEhAI any_word)*)? (LOhAI spaces? (!LOhAI !LEhAI any_word)*)? LEhAI spaces?
LOhAI_post <- post_clause

LOhOI_clause <- LOhOI_pre LOhOI_post
LOhOI_pre <- pre_clause LOhOI spaces?
LOhOI_post <- post_clause

MEhOI_clause <- MEhOI_pre MEhOI_post
MEhOI_pre <- pre_clause MEhOI spaces? zohoi_word spaces?
MEhOI_post <- post_clause

NOIhA_clause <- NOIhA_pre NOIhA_post
NOIhA_pre <- pre_clause NOIhA spaces?
NOIhA_post <- post_clause

KUhAU_clause <- KUhAU_pre KUhAU_post
KUhAU_pre <- pre_clause KUhAU spaces?
KUhAU_post <- post_clause

ZOhOI_clause <- ZOhOI_pre ZOhOI_post
ZOhOI_pre <- pre_clause ZOhOI spaces? zohoi_word spaces?
ZOhOI_post <- post_clause

# END BETA: Experimental selmaho


# ___ MORPHOLOGY ___

CMEVLA <- cmevla
BRIVLA <- gismu / lujvo / fuhivla

# BETA: GOhOI / KUhAU / LEhAI / LOhAI / LOhOI / NOIhA / ZOhOI / MEhOI / IAU
CMAVO <- A / BAI / BAhE / BE / BEI / BEhO / BIhE / BIhI / BO / BOI / BU / BY / CAhA / CAI / CEI / CEhE / CO / COI / CU / CUhE / DAhO / DOI / DOhU / FA / FAhA / FAhO / FEhE / FEhU / FIhO / FOI / FUhA / FUhE / FUhO / GA / GAhO / GEhU / GI / GIhA / GOI / GOhA / GOhOI / GUhA / I / IAU / JA / JAI / JOhI / JOI / KE / KEhE / KEI / KI / KOhA / KU / KUhAU / KUhE / KUhO / LA / LAU / LAhE / LE / LEhAI / LEhU / LI / LIhU / LOhAI / LOhO / LOhOI / LOhU / LU / LUhU / MAhO / MAI / ME / MEhOI / MEhU / MOhE / MOhI / MOI / NA / NAI / NAhE / NAhU / NIhE / NIhO / NOI / NOIhA / NU / NUhA / NUhI / NUhU / PA / PEhE / PEhO / PU / RAhO / ROI / SA / SE / SEI / SEhU / SI / SOI / SU / TAhE / TEhU / TEI / TO / TOI / TUhE / TUhU / UI / VA / VAU / VEI / VEhO / VUhU / VEhA / VIhA / VUhO / XI / ZAhO / ZEhA / ZEI / ZI / ZIhE / ZO / ZOI / ZOhOI / ZOhU / cmavo

# This is a Parsing Expression Grammar for the morphology of Lojban.
# See http://www.pdos.lcs.mit.edu/~baford/packrat/
#
# All rules have the form
#
# name = peg_expression
#
# which means that the grammatical construct "name" is parsed using
# "peg_expression".
#
# 1) Concatenation is expressed by juxtaposition with no operator symbol.
# 2) / represents *ORDERED* alternation (choice). If the first
# option succeeds, the others will never be checked.
# 3) ? indicates that the element to the left is optional.
# 4) * represents optional repetition of the construct to the left.
# 5) + represents one_or_more repetition of the construct to the left.
# 6) () serves to indicate the grouping of the other operators.
# 7) & indicates that the element to the right must follow (but the
# marked element itself does not absorb anything).
# 8) ! indicates that the element to the right must not follow (the
# marked element itself does not absorb anything).
# 9) . represents any character.
# 10) ' ' or " " represents a literal string.
# 11) [] represents a character class.
#
# Repetitions grab as much as they can.
#
#
# ___ GRAMMAR ___
# This grammar classifies words by their morphological class (cmevla,
# gismu, lujvo, fuhivla, cmavo, and non_lojban_word).
#
#The final section sorts cmavo into grammatical classes (A, BAI, BAhE, ..., ZOhU).
#
# mi'e ((xorxes))

#___________________________________________________________________

# words = expr:(pause? (word pause?)*) { return _join(expr); }

# word = expr:lojban_word / non_lojban_word { return expr; }

# lojban_word = expr:(cmevla / cmavo / brivla) { return expr; }
lojban_word <- CMEVLA / CMAVO / BRIVLA

any_word <- lojban_word spaces?

# === ZOI quote handling ===

# Pure PEG cannot handle ZOI quotes, because it cannot check whether the closing
# delimiter is the same as the opening one.
# ZOI quote handling is the only part of Lojban's grammar that needs mechanisms
# external to the pure PEG grammar to be implemented properly; those mechanisms
# are implementation-specific.

zoi_open <- lojban_word  #: PUSH
# Non-PEG: Remember the value matched by this zoi_open.

zoi_word_2 <- non_space+  #: LEAF

zoi_word <- zoi_word_2 #: PEEK-DIFF
# Non-PEG: Match successfully only if different from the most recent zoi_open.

zoi_close <- any_word  #: POP-EQ
# Non-PEG: Match successfully only if identical to the most recent zoi_open.

# BETA: ZOhOI, MEhOI
zohoi_word <- non_space+

#___________________________________________________________________

cmevla <- jbocme / zifcme

zifcme <- !h (nucleus / glide / h / consonant !pause / digit)* consonant &pause

jbocme <- &zifcme (any_syllable / digit)+ &pause

#cmevla = !h cmevla_syllable* &consonant coda? consonantal_syllable* onset &pause

#cmevla_syllable = !doi_la_lai_lahi coda? consonantal_syllable* onset nucleus / digit

#doi_la_lai_lahi = (d o i / l a (h? i)?) !h !nucleus

#___________________________________________________________________

cmavo <- !cmevla !CVCy_lujvo cmavo_form &post_word

CVCy_lujvo <- CVC_rafsi y h? initial_rafsi* brivla_core / stressed_CVC_rafsi y short_final_rafsi

cmavo_form <- !h !cluster onset (nucleus h)* (!stressed nucleus / nucleus !cluster) / y+ / digit

#___________________________________________________________________

brivla <- !cmavo initial_rafsi* brivla_core

brivla_core <- fuhivla / gismu / CVV_final_rafsi / stressed_initial_rafsi short_final_rafsi

stressed_initial_rafsi <- stressed_extended_rafsi / stressed_y_rafsi / stressed_y_less_rafsi

initial_rafsi <- extended_rafsi / y_rafsi / !any_extended_rafsi y_less_rafsi !any_extended_rafsi

#___________________________________________________________________

any_extended_rafsi <- fuhivla / extended_rafsi / stressed_extended_rafsi

fuhivla <- fuhivla_head stressed_syllable consonantal_syllable* final_syllable

stressed_extended_rafsi <- stressed_brivla_rafsi / stressed_fuhivla_rafsi

extended_rafsi <- brivla_rafsi / fuhivla_rafsi

stressed_brivla_rafsi <- &unstressed_syllable brivla_head stressed_syllable h y

brivla_rafsi <- &(syllable consonantal_syllable* syllable) brivla_head h y h?

stressed_fuhivla_rafsi <- fuhivla_head stressed_syllable consonantal_syllable* !h onset y

fuhivla_rafsi <- &unstressed_syllable fuhivla_head !h onset y h?

fuhivla_head <- !rafsi_string brivla_head

brivla_head <- !cmavo !slinkuhi !h &onset unstressed_syllable*

slinkuhi <- !rafsi_string consonant rafsi_string

rafsi_string <- y_less_rafsi* (gismu / CVV_final_rafsi / stressed_y_less_rafsi short_final_rafsi / y_rafsi / stressed_y_rafsi / stressed_y_less_rafsi? initial_pair y / hy_rafsi / stressed_hy_rafsi)

#___________________________________________________________________

gismu <- (initial_pair stressed_vowel / consonant stressed_vowel consonant) &final_syllable consonant vowel &post_word

CVV_final_rafsi <- consonant stressed_vowel h &final_syllable vowel &post_word

short_final_rafsi <- &final_syllable (consonant diphthong / initial_pair vowel) &post_word

stressed_y_rafsi <- (stressed_long_rafsi / stressed_CVC_rafsi) y

stressed_y_less_rafsi <- stressed_CVC_rafsi !y / stressed_CCV_rafsi / stressed_CVV_rafsi

stressed_long_rafsi <- initial_pair stressed_vowel consonant / consonant stressed_vowel consonant consonant

stressed_CVC_rafsi <- consonant stressed_vowel consonant

stressed_CCV_rafsi <- initial_pair stressed_vowel

stressed_CVV_rafsi <- consonant (unstressed_vowel h stressed_vowel / stressed_diphthong) r_hyphen?

y_rafsi <- (long_rafsi / CVC_rafsi) y h?

y_less_rafsi <- !y_rafsi !stressed_y_rafsi !hy_rafsi !stressed_hy_rafsi (CVC_rafsi / CCV_rafsi / CVV_rafsi) !h

hy_rafsi <- (long_rafsi vowel / CCV_rafsi / CVV_rafsi) h y h?

stressed_hy_rafsi <- (long_rafsi stressed_vowel / stressed_CCV_rafsi / stressed_CVV_rafsi) h y

long_rafsi <- initial_pair unstressed_vowel consonant / consonant unstressed_vowel consonant consonant

CVC_rafsi <- consonant unstressed_vowel consonant

CCV_rafsi <- initial_pair unstressed_vowel

CVV_rafsi <- consonant (unstressed_vowel h unstressed_vowel / unstressed_diphthong) r_hyphen?

r_hyphen <- r &consonant / n &r

#___________________________________________________________________

final_syllable <- onset !y !stressed nucleus !cmevla &post_word

stressed_syllable <- &stressed syllable / syllable &stress

stressed_diphthong <- &stressed diphthong / diphthong &stress

stressed_vowel <- &stressed vowel / vowel &stress

unstressed_syllable <- !stressed syllable !stress / consonantal_syllable

unstressed_diphthong <- !stressed diphthong !stress

unstressed_vowel <- !stressed vowel !stress

#// FIX: Xorxes' fix for fu'ivla rafsi stress
stress <- (consonant / glide)* h? y? syllable pause

stressed <- onset comma* [AEIOU]

any_syllable <- onset nucleus coda? / consonantal_syllable

syllable <- onset !y nucleus coda?

#// FIX: preventing {bla'ypre} from being a valid lujvo
consonantal_syllable <- consonant &syllabic coda

coda <- !any_syllable consonant &any_syllable / syllabic? consonant? &pause

onset <- h / glide / initial

nucleus <- vowel / diphthong / y !nucleus

#_________________________________________________________________

glide <- (i / u) &nucleus

diphthong <- (a i !i / a u !u / e i !i / o i !i) !nucleus

vowel <- (a / e / i / o / u) !nucleus

a <- comma* [aA]

e <- comma* [eE]

i <- comma* [iI]

o <- comma* [oO]

u <- comma* [uU]

y <- comma* [yY] !(!y nucleus)



#___________________________________________________________________

cluster <- consonant consonant+

initial_pair <- &initial consonant consonant !consonant

initial <- (affricate / sibilant? other? liquid?) !consonant !glide

affricate <- t c / t s / d j / d z

liquid <- l / r

other <- p / t !l / k / f / x / b / d !l / g / v / m / n !liquid

sibilant <- c / s !x / (j / z) !n !liquid

consonant <- voiced / unvoiced / syllabic

syllabic <- l / m / n / r

voiced <- b / d / g / j / v / z

unvoiced <- c / f / k / p / s / t / x

l <- comma* [lL] !h !glide !l

m <- comma* [mM] !h !glide !m !z

n <- comma* [nN] !h !glide !n !affricate

r <- comma* [rR] !h !glide !r

b <- comma* [bB] !h !glide !b !unvoiced

d <- comma* [dD] !h !glide !d !unvoiced

g <- comma* [gG] !h !glide !g !unvoiced

v <- comma* [vV] !h !glide !v !unvoiced

j <- comma* [jJ] !h !glide !j !z !unvoiced

z <- comma* [zZ] !h !glide !z !j !unvoiced

s <- comma* [sS] !h !glide !s !c !voiced

c <- comma* [cC] !h !glide !c !s !x !voiced

x <- comma* [xX] !h !glide !x !c !k !voiced

k <- comma* [kK] !h !glide !k !x !voiced

f <- comma* [fF] !h !glide !f !voiced

p <- comma* [pP] !h !glide !p !voiced

t <- comma* [tT] !h !glide !t !voiced

h <- comma* ['h] &nucleus

#___________________________________________________________________

digit <- comma* [0123456789] !h !nucleus

post_word <- pause / !nucleus lojban_word

pause <- comma* space_char+ / EOF

EOF <- comma* !.

comma <- [,]

# This is an orphan rule.
non_lojban_word <- !lojban_word non_space+

non_space <- !space_char .  #: JOIN

#Unicode_style and escaped chars not compatible with cl_peg
space_char <- [.\t\n\r?!\u0020]  #: JOIN

# space_char = [.?! ] / space_char1 / space_char2
# space_char1 = '    '
# space_char2 = ''

#___________________________________________________________________

spaces <- !Y initial_spaces

initial_spaces <- (comma* space_char / !ybu Y)+ EOF? / EOF  #: LEAF

ybu <- Y space_char* BU

lujvo <- !gismu !fuhivla brivla

#___________________________________________________________________

A <- &cmavo ( a / e / j i / o / u ) &post_word

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_word

BAhE <- &cmavo ( b a h e / z a h e ) &post_word

BE <- &cmavo ( b e ) &post_word

BEI <- &cmavo ( b e i ) &post_word

BEhO <- &cmavo ( b e h o ) &post_word

BIhE <- &cmavo ( b i h e ) &post_word

BIhI <- &cmavo ( m i h i / b i h o / b i h i ) &post_word

BO <- &cmavo ( b o ) &post_word

BOI <- &cmavo ( b o i ) &post_word

BU <- &cmavo ( b u ) &post_word

# BETA: a'y, e'y, i'y, o'y, u'y, iy, uy
BY <- &cmavo ( ybu / 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 / a h y / e h y / i h y / o h y / u h y / i y / u 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_word

# BETA: bi'ai
CAhA <- &cmavo ( b i h a i / c a h a / p u h i / n u h o / k a h e ) &post_word

CAI <- &cmavo ( p e i / c a i / c u h i / s a i / r u h e ) &post_word

CEI <- &cmavo ( c e i ) &post_word

CEhE <- &cmavo ( c e h e ) &post_word

CO <- &cmavo ( c o ) &post_word

# BETA: di'ai, jo'au, co'oi, da'oi, ki'ai, sa'ei
COI <- &cmavo ( d i h a i / j o h a u / c o h o i / d a h o i / k i h a i / s a h e i / 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_word

CU <- &cmavo ( c u ) &post_word

CUhE <- &cmavo ( c u h e / n a u ) &post_word

DAhO <- &cmavo ( d a h o ) &post_word

DOI <- &cmavo ( d o i ) &post_word

DOhU <- &cmavo ( d o h u ) &post_word

FA <- &cmavo ( f a i / f a / f e / f o / f u / f i h a / f i ) &post_word

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_word &post_word

FAhO <- &cmavo ( f a h o ) &post_word

FEhE <- &cmavo ( f e h e ) &post_word

FEhU <- &cmavo ( f e h u ) &post_word

FIhO <- &cmavo ( f i h o ) &post_word

FOI <- &cmavo ( f o i ) &post_word

FUhA <- &cmavo ( f u h a ) &post_word

FUhE <- &cmavo ( f u h e ) &post_word

FUhO <- &cmavo ( f u h o ) &post_word

GA <- &cmavo ( g e h i / g e / g o / g a / g u ) &post_word

GAhO <- &cmavo ( k e h i / g a h o ) &post_word

GEhU <- &cmavo ( g e h u ) &post_word

GI <- &cmavo ( g i ) &post_word

GIhA <- &cmavo ( g i h e / g i h i / g i h o / g i h a / g i h u ) &post_word

GOI <- &cmavo ( n o h u / n e / g o i / p o h u / p e / p o h e / p o ) &post_word

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_word

GUhA <- &cmavo ( g u h e / g u h i / g u h o / g u h a / g u h u ) &post_word

I <- &cmavo ( i ) &post_word

JA <- &cmavo ( j e h i / j e / j o / j a / j u ) &post_word

JAI <- &cmavo ( j a i ) &post_word

JOhI <- &cmavo ( j o h i ) &post_word

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_word

KE <- &cmavo ( k e ) &post_word

KEhE <- &cmavo ( k e h e ) &post_word

KEI <- &cmavo ( k e i ) &post_word

KI <- &cmavo ( k i ) &post_word

# BETA: xai, zu'ai
KOhA <- &cmavo ( z u h a i / 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 / x a i / d a / d e / d i / k o / m i / d o ) &post_word

KU <- &cmavo ( k u ) &post_word

KUhE <- &cmavo ( k u h e ) &post_word

KUhO <- &cmavo ( k u h o ) &post_word

# BETA: la'ei
LA <- &cmavo ( l a h e i / l a i / l a h i / l a ) &post_word

LAU <- &cmavo ( c e h a / l a u / z a i / t a u ) &post_word

# BETA: zo'ei
LAhE <- &cmavo ( z o h e i / 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_word

# BETA: me'ei, mo'oi, ri'oi
LE <- &cmavo ( m e h e i / m o h o i / r i h o i / 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_word

LEhU <- &cmavo ( l e h u ) &post_word

LI <- &cmavo ( m e h o / l i ) &post_word

LIhU <- &cmavo ( l i h u ) &post_word

LOhO <- &cmavo ( l o h o ) &post_word

LOhU <- &cmavo ( l o h u ) &post_word

# BETA: la'au
LU <- &cmavo ( l a h a u / l u ) &post_word

LUhU <- &cmavo ( l u h u ) &post_word

MAhO <- &cmavo ( m a h o ) &post_word

# BETA: ju'ai
MAI <- &cmavo ( m o h o / m a i / j u h a i ) &post_word

# BETA: me'au
ME <- &cmavo (m e h a u / m e) &post_word

MEhU <- &cmavo ( m e h u ) &post_word

MOhE <- &cmavo ( m o h e ) &post_word

MOhI <- &cmavo ( m o h i ) &post_word

MOI <- &cmavo ( m e i / m o i / s i h e / c u h o / v a h e ) &post_word

NA <- &cmavo ( j a h a / n a ) &post_word

# BETA: ja'ai
NAI <- &cmavo ( n a i / j a h a i ) &post_word

NAhE <- &cmavo ( t o h e / j e h a / n a h e / n o h e ) &post_word

# BETA: ji'oi
NAhU <- &cmavo ( n a h u / j i h o i ) &post_word

NIhE <- &cmavo ( n i h e ) &post_word

NIhO <- &cmavo ( n i h o / n o h i ) &post_word

NOI <- &cmavo ( v o i / n o i / p o i ) &post_word

# BETA: poi'i, kai'u
NU <- &cmavo ( p o i h i / k a i h u / 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_word

NUhA <- &cmavo ( n u h a ) &post_word

NUhI <- &cmavo ( n u h i ) &post_word

NUhU <- &cmavo ( n u h u ) &post_word

# BETA: xo'e, su'oi, ro'oi
PA <- &cmavo ( s u h o i / r o h o i / x o h e / 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_word

PEhE <- &cmavo ( p e h e ) &post_word

PEhO <- &cmavo ( p e h o ) &post_word

PU <- &cmavo ( b a / p u / c a ) &post_word

RAhO <- &cmavo ( r a h o ) &post_word

# BETA: va'ei, mu'ei
ROI <- &cmavo ( r e h u / r o i / v a h e i / m u h e i ) &post_word

SA <- &cmavo ( s a ) &post_word

SE <- &cmavo ( s e / t e / v e / x e ) &post_word

SEI <- &cmavo ( s e i / t i h o ) &post_word

SEhU <- &cmavo ( s e h u ) &post_word

# BETA: ze'ei
SI <- &cmavo ( z e h e i / s i ) &post_word

# BETA: New-SOI, soi, xoi
SOI <- &cmavo ( s o i / x o i ) &post_word

SU <- &cmavo ( s u ) &post_word

TAhE <- &cmavo ( r u h i / t a h e / d i h i / n a h o ) &post_word

TEhU <- &cmavo ( t e h u ) &post_word

TEI <- &cmavo ( t e i ) &post_word

TO <- &cmavo ( t o h i / t o ) &post_word

TOI <- &cmavo ( t o i ) &post_word

TUhE <- &cmavo ( t u h e ) &post_word

TUhU <- &cmavo ( t u h u ) &post_word

# BETA: ko'oi, si'au, o'ai, xe'e, xo'o
UI <- &cmavo ( k o h o i / s i h a u / a h o i / o h a i / x e h e / x o h o / 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_word

VA <- &cmavo ( v i / v a / v u ) &post_word

VAU <- &cmavo ( v a u ) &post_word

VEI <- &cmavo ( v e i ) &post_word

VEhO <- &cmavo ( v e h o ) &post_word

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_word

VEhA <- &cmavo ( v e h u / v e h a / v e h i / v e h e ) &post_word

VIhA <- &cmavo ( v i h i / v i h a / v i h u / v i h e ) &post_word

VUhO <- &cmavo ( v u h o ) &post_word

XI <- &cmavo ( x i ) &post_word

Y <- &cmavo ( y+ ) &post_word

# BETA: xa'o
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 / x a h o ) &post_word

ZEhA <- &cmavo ( z e h u / z e h a / z e h i / z e h e ) &post_word

ZEI <- &cmavo ( z e i ) &post_word

ZI <- &cmavo ( z u / z a / z i ) &post_word

ZIhE <- &cmavo ( z i h e ) &post_word

# BETA: ma'oi
ZO <- &cmavo ( z o / m a h o i ) &post_word

ZOI <- &cmavo ( z o i / l a h o ) &post_word

# BETA: ce'ai
ZOhU <- &cmavo ( c e h a i / z o h u ) &post_word

# BEGIN BETA: Experimental selmaho

GOhOI <- &cmavo ( g o h o i ) &post_word
IAU <- &cmavo ( i a u ) &post_word
KUhAU <- &cmavo ( k u h a u ) &post_word
LEhAI <- &cmavo ( l e h a i ) &post_word
LOhAI <- &cmavo ( l o h a i / s a h a i ) &post_word
LOhOI <- &cmavo ( l o h o i / x u h u ) &post_word
NOIhA <- &cmavo ( n o i h o h a / p o i h o h a / n o i h a / p o i h a / s o i h a ) &post_word
ZOhOI <- &cmavo ( z o h o i / l a h o i / r a h o i ) &post_word
MEhOI <- &cmavo ( m e h o i ) &post_word

# END BETA: Experimental selmaho