! Divvun & Giellatekno - open source grammars for Sámi and other languages
! Copyright © 2000-2010 The University of Tromsø & the Norwegian Sámi Parliament
! http://giellatekno.uit.no & http://divvun.no
!
! This program is free software. You can redistribute and/or modify
! this file under the terms of the GNU General Public License as published by
! the Free Software Foundation, either version 3 of the License, or
! (at your option) any later version. The GNU General Public License
! is found at http://www.gnu.org/licenses/gpl.html. It is
! also available in the file $GTHOME/LICENSE.txt.
!
! Other licensing options are available upon request, please contact
! giellatekno@hum.uit.no or feedback@divvun.no

# This filter removes all strings containing derivational tags
# as defined below.
# Further, we check that we don't have double passives.
# See smX-lex.txt for more documentation.
#
# The filter should be applied on top of the nonrec transducer.

# Insert default compounding tag if there is no compounding tag before the
# POS tag, possibly with an intervening OLang/XXX tag in between (the semantic
# tag has been removed in an earlier step):

#  All contexts: block insertion if there is an OLang or a CmpN tag to the left.

# First context: nouns, bare POS tag:
 "+CmpN/SgN" <- [. 0 .] || ! Anchor left context at beginning of the word:
                           [ .#. | %- | %# ]
                               ! ... then followed by anything that is not one of these tags
                               ! essentially blocking addition of default tags after derivations
                               ! that is: lemma symbols until you get to the ...
                               \[ "+CmpN/SgN"
                                | "+CmpN/SgG"
                                | "+CmpN/PlN"
                                | "+CmpN/PlG"
                                | "+CmpN/SgNomLeft"
                                | "+CmpN/SgGenLeft"
                                | "+CmpN/PlGenLeft"
                                ]+
                            ! ... POS tag:
                            [ "+N" ] _
                               ! unless followed by any of these tags:
                               \[ "+CmpN/SgN"
                                | "+CmpN/SgG"
                                | "+CmpN/PlN"
                                | "+CmpN/PlG"
                                | "+CmpN/SgNomLeft"
                                | "+CmpN/SgGenLeft"
                                | "+CmpN/PlGenLeft"
                                ]+
                                ! stopping at the end of the word/lemma
                                [  "+Cmp"
                                 | "+Der" | "+Der1" | "+Der2" | "+Der3" | "+Der4" | "+Der5"
                                 | .#. | %- | %>
                                 | %#
                                ]

! All in all: add default compounding tags only if there is nothing, and never after a derivation.
! Derivations can have their own compounding tags, but they must always be explicitly stated.

.o.

# Third context: adjectives - always insert CmpN/Attr:
 "+CmpN/Attr" <- [. 0 .] || [ "+A" | "+PrsPrc" ] _
;

# In all other contexts, there is already a +CmpN/ tag, and thus we do NOT want
# to insert the default tag.