mirror of
https://github.com/GrammaticalFramework/gf-rgl.git
synced 2026-08-22 12:16:23 -06:00
aarneranta
8c4cd58bd1
Adding Polish to informath (grammars/next) exposed a set of gaps. Unlike
Czech, StructuralPol was already complete; what was missing was a handful
of lins, a way to govern the nominative, and some outright mistakes.
Missing lins, all reached as qualified Grammar.X by the application's
functors and so not shimmable from the application side:
AdjectivePol AdvAP
SentencePol SSubjS
IdiomPol ImpP3
StructuralPol that_Subj
MarkupPol new module (Markup is not part of the RGL build script,
so it is compiled on demand, as MarkupCze is)
ParadigmsPol mkAdv (every other ParadigmsX has it; the application
interfaces reach it as Paradigms.mkAdv)
ImpP3 has no third-person imperative to use, so it takes the standard
"niech" periphrasis. The copula takes the future ("niech x będzie grupą")
and every other verb the present ("niech x należy do A"): być is the only
Polish verb with a synthetic future, and imienne marks exactly the copular
VPs.
NomPrep: ComplCase had no nominative at all, so "jako", "niż" and
"zdefiniowany jako" -- all of which govern the nominative -- came out
locative ("mniejszy niż liczbie"). mkCompl now maps Nom to a new NomPrep,
and the dep tables of the pronouns, nounPN, mkPN and the structural NPs
cover it. LexiconNounPol is marked DO NOT EDIT, but paris_PN and john_PN
inline their own dep tables and so had to be extended too.
Two corrections:
VerbPol.CompCN used the nominative for a predicative noun, giving
"x jest grupa"; Polish uses the instrumental, as CompNP right below it
already does.
ExtendPol.ExistsNP inherited ExistNP from ExtendFunctor, giving
"jest macierz". Polish distinguishes the two: "there exists" is istnieć,
which is what mathematical prose uses.
ParadigmsPol.guess_paradigm_basic never matched -ość, the productive
feminine abstract suffix, so sprzeczność took a masculine declension
(*sprzeczności/a, *sprzecznościowi) despite being tagged feminine. It now
routes to the kość paradigm.
Also documents, without changing, why the 2-string mkN throws its genitive
away: guess_paradigm's 2-string table is unsound (its first branch matches
every noun in -a, and its branches disagree about whether mkNTable* takes
the nominative or the bare stem), so passing sggen to it turns
"liczba"/"liczby" into *liczbaa. The 1-string guesser is the sound path
until that table is repaired.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
125 lines
4.0 KiB
Plaintext
125 lines
4.0 KiB
Plaintext
--# -path=.:../abstract:../common:../prelude
|
||
|
||
-- Ilona Nowak Wintersemester 2007/08
|
||
|
||
-- Adam Slaski, 2009, 2010 <adam.slaski@gmail.com>
|
||
|
||
-- In Polish language they aren't determiners like in english or german.
|
||
|
||
concrete StructuralPol of Structural = CatPol **
|
||
open ResPol, MorphoPol, Prelude in {
|
||
|
||
|
||
flags optimize=all; coding=utf8;
|
||
|
||
lin
|
||
|
||
above_Prep = nadPrep;
|
||
after_Prep = mkPrep "po" Loc;
|
||
|
||
all_Predet = { s=wszystek; np=wszystko; adj=True };
|
||
almost_AdA, almost_AdN = ss "prawie";
|
||
although_Subj = ss "pomimo";
|
||
always_AdV = ss "zawsze";
|
||
and_Conj = {s1=""; s2 = "i"; sent1=""; sent2=["i"]};
|
||
at_least_AdN = ss "co najmniej";
|
||
at_most_AdN = ss "co najwyżej";
|
||
because_Subj = ss "ponieważ";
|
||
before_Prep = mkPrep "przed" Instr;
|
||
behind_Prep = mkPrep "za" Instr;
|
||
between_Prep = mkPrep "między" Instr;
|
||
both7and_DConj = {s1="zarówno"; s2=["jak i"]; sent1="zarówno"; sent2=[", jak i"]};
|
||
but_PConj = ss "ale";
|
||
by8agent_Prep = mkPrep "przez" Acc;
|
||
by8means_Prep = mkPrep "przez" Acc;
|
||
can8know_VV = mkItVerb (mkMonoVerb "umieć" conj101 Imperfective);
|
||
can_VV = mkItVerb (mkMonoVerb "móc" conj27 Imperfective);
|
||
during_Prep = mkPrep "podczas" Gen;
|
||
either7or_DConj = {s1="albo"; s2="albo"; sent1="albo"; sent2=[", albo"]};
|
||
every_Det = kazdyDet;
|
||
everybody_NP = wszyscy;
|
||
everything_NP = wszystko;
|
||
everywhere_Adv = ss "wszędzie";
|
||
except_Prep = mkPrep "z wyjątkiem" Acc;
|
||
few_Det = pareDet;
|
||
for_Prep = mkPrep "dla" Gen;
|
||
from_Prep = zGenPrep;
|
||
have_V2 = dirV2 (mkMonoVerb "mieć" conj100 Imperfective);
|
||
he_Pron = pronOn;
|
||
here_Adv = ss "tutaj";
|
||
here7to_Adv = ss "tutaj";
|
||
here7from_Adv = ss "stąd";
|
||
how_IAdv = ss "jak";
|
||
how8many_IDet = ileDet;
|
||
i_Pron = pronJa MascPersSg;
|
||
if_Subj = ss "jeśli";
|
||
if_then_Conj = {s1="jeżeli"; s2=[", to"]; sent1="jeżeli"; sent2=[", to"]};
|
||
in8front_Prep = mkPrep "przed" Instr;
|
||
in_Prep = mkPrep "w" Loc;
|
||
it_Pron = pronOno;
|
||
language_title_Utt = ss "polski";
|
||
less_CAdv = {s,sn = "mniej" ; p,pn = "niż" } ;
|
||
many_Det = wieleDet;
|
||
more_CAdv = {s = "bardziej" ; pn,p = "niż"; sn="więcej"} ;
|
||
most_Predet = { s=wszystek; np={nom="większość"; voc="większości";
|
||
dep=table{AccPrep|AccNoPrep=>"większość"; InstrC=>"większością"; _=>"większości"};
|
||
p=P3; gn=FemSg}; adj=False };
|
||
much_Det = duzoDet;
|
||
must_VV = mkItVerb (mkMonoVerb "musieć" conj93 Imperfective);
|
||
no_Quant = zadenQuant;
|
||
no_Utt = ss "nie";
|
||
nobody_NP = niktNP;
|
||
not_Predet = { s=zadenQuant.s; np=wszystko; adj=True };
|
||
nothing_NP = nicNP;
|
||
on_Prep = mkPrep "nа" Loc;
|
||
only_Predet = { s=\\_=>"tylko"; np=wszystko; adj=True };
|
||
or_Conj = {s1=""; s2="lub"; sent1=""; sent2=["lub"]};
|
||
otherwise_PConj = ss "inaczej";
|
||
part_Prep = mkPrep "z" Gen;
|
||
please_Voc = ss "proszę";
|
||
possess_Prep = mkPrep "" Gen; --overgenerating with pronouns
|
||
quite_Adv = ss "całkiem";
|
||
she_Pron = pronOna;
|
||
so_AdA = ss "tak";
|
||
somebody_NP = ktos ;
|
||
someSg_Det = pewienDet;
|
||
somePl_Det = pewniDet;
|
||
something_NP = cos ;
|
||
somewhere_Adv = ss "gdzieś";
|
||
that_Quant = demPronTen "tamten";
|
||
-- Polish always sets off a "że" clause with a comma, so the subordinator
|
||
-- carries it, as IdiomPol/SentencePol already do for EmbedS and SlashVS
|
||
that_Subj = ss [", że"];
|
||
there_Adv = ss "tam";
|
||
there7to_Adv = ss "tam";
|
||
there7from_Adv = ss "stamtąd";
|
||
therefore_PConj = ss "dlatego";
|
||
they_Pron = pronOni;
|
||
this_Quant = demPronTen "ten";
|
||
through_Prep = mkPrep "przez" Acc;
|
||
to_Prep = doPrep;
|
||
too_AdA = ss "za";
|
||
under_Prep = mkPrep "pod" Instr; -- with Acc too
|
||
very_AdA = ss "bardzo";
|
||
want_VV = mkV "chcieć" conj45 "zechcieć" conj45;
|
||
we_Pron = pronMy;
|
||
whatPl_IP = co;
|
||
whatSg_IP = co;
|
||
when_IAdv = ss "kiedy";
|
||
when_Subj = ss "jeśli";
|
||
where_IAdv = ss "gdzie";
|
||
which_IQuant = { s = ktory };
|
||
whoPl_IP = kto;
|
||
whoSg_IP = kto;
|
||
why_IAdv = ss "dlaczego";
|
||
with_Prep = mkPrep "z" Instr;
|
||
without_Prep = mkPrep "bez" Gen;
|
||
youPl_Pron = pronWy;
|
||
yes_Utt = ss "tak";
|
||
youSg_Pron = pronTy MascPersSg;
|
||
youPol_Pron = pronWy;
|
||
|
||
as_CAdv = { s,sn="tak"; p,pn="jak"} ;
|
||
|
||
};
|