!!!Møte 16. desember 2016

Hangouts: Kevin, Trond, Lene

!!Saker:
# Strukturen i sme-nob vs. sme-smX
# Debugging av regr test
# Modes
# hfst vs bin (notater)
# Feilmeldingar
# Regresjonstestar


!!Strukturen i sme-nob vs. sme-smX
* apertium-sme-nob.sme-nob.val - ikke i bruk
* apertium-sme-nob.sme-nob.lex

!hfst vs bin

Kommando for å analysere sme:

{{{
echo ja|hfst-lookup .deps/sme-nob.automorf-trimmed.hfst 
echo ja|hfst-lookup .deps/sme.automorf.hfst 

make nob-sme # lagar nob→sme-filene
echo "sátni<n><sg><acc>" | hfst-lookup .deps/sme.autogen.hfst 
}}}


Norsk skal vi analysere slik:
{{{
echo "hei" |  lt-proc -e ../../languages/apertium-nob/nob.automorf.bin 
(-e må med for å ha analyse av (dynamisk) samansette ord)

$ echo "hei" | apertium -d ../../languages/apertium-nob nob-morph 
^hei/heie<vblex><imp>/hei<n><m><sg><ind>/hei<n><f><sg><ind>/hei<n><m><sg><ind>/hei<n><f><sg><ind>$^./.<sent><clb>$

Slik gjer Kevin (denne klarer også dynamisk samansette ord):
$ echo "hei" | apertium -d . unob-sme-morph 
}}}

{{{
echo Regjeringen | apertium -d . unob-sme-morph 
^Regjeringen/Regjeringen<np><cog>/regjering<n><m><sg><def>/regjering<n><m><sg><def>$^./.<sent><clb>$

"<Ráđđehus>"
        "ráđđehus" N <sme> Sem/Org Sg Nom
        
 <e><p><l>ráđđehus<s n="n"/><s n="org"/></l><r>regjering<s n="n"/></r></p><par n="m_RL_f__n"/></e>
       

<e><p><l>ráđđehus<s n="n"/><s n="sem_org"/></l><r>regjering<s n="n"/></r></p><par n="m_RL_f__n"/></e>
<e><p><l>Regjeringen<s n="np"/><s n="sem_org"/></l><r>Regjeringen<s n="np"/></r></p></e>
}}}

nob-morph skil seg frå lt-proc ved å godta reserverte teikn.

(og hugsar alltid å ta med -e)


!!Debugging av regr test

!Pronomen
* prn får un
* 1. person får mf

{{{
echo jeg|apertium -d nob nob-morph
^jeg/jeg<n><nt><sg><ind>/jeg<n><nt><pl><ind>/jeg<prn><pers><p1><mf><sg><nom>$^./.<sent><clb>$

$ echo "mun lean dáppe"|apertium -d. sme-nob-postchunk
^jeg<prn><pers><p1><mf><sg><nom>$ ^være<vblex><pres>$ ^her<adv>$^.<sent><clb>$

echo "mun lean dáppe"|apertium -d. sme-nob
#jeg er her

$ echo '^jeg<prn><pers><p1><mf><sg><nom>$'|lt-proc -g sme-nob.autogen.bin 
jeg

echo '^jeg<prn><pers><p1><mf><sg><nom>$'|lt-proc -g sme-nob.autogen.bin 
#jeg

apertium-sme-nob$ echo "mun lean dáppe"|apertium -d. sme-nob-dgen
#jeg<prn><p1><mf><sg><nom> er her

echo "Son oaidná mu."|apertium -d. sme-nob-postchunk
^Han<prn><pers><p3><m><sg><nom>$ ^se<vblex><pres>$ ^jeg<prn><pers><p1><mf><sg><acc>$^..<sent><clb>$
}}}

cd ../../languages/apertium-nob
svn up && make

Taggstrengane er identisk (gjeld også 3. person), men vi får likevel #.


!Eigennamn
* propernouns: fjerne sem_sur og cog og top i bidix

{{{
<e><p><l>bidjat<s n="vblex"/><s n="tv"/></l><r>sette<s n="vblex"/><s n="pers"/></r></p><par n="__verb"/></e>
}}}

Mathisen sem_sur    -   Mathisen   cog  

{{{
<e><p><l>Mathisen<s n="np"/></l><r>Mathisen<s n="np"/></r></p><par n="__np"/></e>
    <pardef n="__np" c="The nob tags are not output by transfer.">

$ echo Mathisenin | apertium -d . sme-nob-dgen
som #Mathisen<np>

^Mathisen<np><cog><ess><@HNOUN>$^.<sent>$

echo Mathisenin | apertium -d. sme-nob
som Mathisen

echo don leat Mathisenin | apertium -d. sme-nob
#du er Mathisen

 echo "Son oaidná mu."|apertium -d. sme-nob-dgen
Montro ser #jeg<prn><p1><mf><sg><acc>.

tf4-hsl-m0024:apertium-sme-nob trond$ echo "Mun lean dáppe."|apertium -d. sme-nob-dgen
#Jeg<prn><p1><mf><sg><nom> er her.

tf4-hsl-m0024:apertium-sme-nob trond$ echo "Son oaidná mu."|apertium -d. sme-nob-morph
^Son/son<pcle>/son<prn><pers><p3><sg><nom>$ ^oaidná/oaidnit<vblex><tv><indic><pres><p3><sg>$ ^mu/mun<prn><pers><p1><sg><acc>/mun<prn><pers><p1><sg><gen>$^../..<sent>$
}}}

{{{
Lene:
echo "Son oaidná mu."|apertium -d. sme-nob
Han ser meg.


sme-nob          Maŋŋá go Máhttolokten doaibmagođii, de lea dát ruhtadoarjja jávkan.
        - Etter at Kunnskapsløftet begynte å fungere, så har denne pengestønaden forsvunnet.
        + Etter at Kunnskapsløftet begynteåfungere, så har denne pengestønaden forsvunnet.
}}}


(ev. endra sem_sur→cog i bidix; sidan me matchar på taggane etter "cog"-taggen òg)



{{{

apertium-sme-nob$ echo Várggát | apertium -d. sme-nob
Vardø
apertium-sme-nob$ echo Mun lean Várggáin | apertium -d. sme-nob
#Jeg er i Vardø

apertium-sme-nob$ echo Mun lean Várggáin | apertium -d. sme-nob-syntax
"<Mun>"
        "mun" prn pers p1 sg nom @SUBJ→ MAP:1673:subj>Pers
"<lean>"
        "leat" vblex iv indic pres p1 sg @+FMAINV
"<Várggáin>"
        "Várggát" np top pl loc @←ADVL-ine MAP:1865:V<advl SELECT:2249
;        "Várggát" np pl loc @←ADVL-ine MAP:1865:V<advl SELECT:2249
"<.>"
        "." sent

apertium-transfer: Rule 46 Mun<prn><pers><p1><sg><nom><@SUBJ^Prn<SN><@SUBJ→><p1><mf><sg><nom>{^jeg<prn><pers><p1><mf><sg><nom>$}$ ^vcop<SV><@+FMAINV><indic><pres><p1><sg><impers><NC>{^være<vblex><pres>$}$ ^caseprep<PR><loc>{^i<pr>$}$ ^nom<SN><ind><pl><loc><impers>{^Vardø<np><top>$}$^default<default>{^.<sent><clb>$}$

echo Mun lean Lene Antonsen | apertium -d. sme-nob-chunker

apertium-transfer: Rule 46 Mun<prn><pers><p1><sg><nom><@SUBJ^Prn<SN><@SUBJ→><p1><mf><sg><nom>{^jeg<prn><pers><p1><mf><sg><nom>$}$ ^vcop<SV><@+FMAINV><indic><pres><p1><sg><impers><NC>{^være<vblex><pres>$}$ ^pre_nom<SN><@←SPRED><ind><f><nom><pers>{^Lene<np><f>$ ^Antonsen<np>$}$^default<default>{^.<sent><clb>$}$


apertium-sme-nob$ usme
Ammerud
Ammerud        Ammerud+N+Prop+Sem/Sur+Sg+Nom
Ammerud        Ammerud+N+Prop+Sem/Sur+Sg+Gen
Ammerud        Ammerud+N+Prop+Sem/Sur+Sg+Acc
Ammerud        Ammerud+N+Prop+Sem/Plc+Sg+Nom
Ammerud        Ammerud+N+Prop+Sem/Plc+Sg+Gen
Ammerud        Ammerud+N+Prop+Sem/Plc+Sg+Acc

22 jahkásaš Tine Chris Mathisen fárrii áibbas okto máddin Sápmái.
#22<det><qnt>un<pl> år gamle Tine Chris Mathisen flyttet helt alene sørfra til Sameland.

$ echo 22 jahkásaš Tine Chris Mathisen fárrii áibbas okto máddin Sápmái.|apertium -d . sme-nob-dgen


$ echo '^Tine<np><ant><f>$'|lt-proc -g ../../languages/apertium-nob/nob.autogen.bin
Tine


^22<num><arab><sg><nom>$ ^ihásâš<adj>$ ^Tine<np><ant><f><attr>$ ^Chris<np><ant><m><attr>$ ^Mathisen<np><sg><nom>$ ^varriđ<vblex><indic><pret><p3><sg>$ ^aaibâs<adv>$ ^ohtuu<adv>$ ^mäddi<n><ess>$ ^Säämi<np><top><sg><ill>$^.<sent>$^.<sent>$


^22<det><qnt>un<pl>$ ^år gammel<adj><sint><pst><un><pl><ind>$ ^Tine<np><f>$ ^Chris<np><m>$ ^Mathisen<np>$ ^flytte<vblex><pret>$ ^helt<adv>$ ^alene<adv>$ ^sørfra<adv>$ ^til<pr>$ ^Sameland<np><top>$^..<sent><clb>$

<e><p><l>Tine<s n="np"/><s n="ant"/><s n="f"/></l><r>Tine<s n="np"/><s n="ant"/><s n="f"/></r></p><par n="__np"/></e>



#22<det><qnt>un<pl> år gammel #Tine<np><f> #Chris<np><m> #Mathisen<np> #han<prn><p3><m><sg><nom> flyttet helt alene sørfra til Sameland.

$ echo Tine|apertium -d . nob-sme-morph 
^Tine/Tine<np><ant><f>$^./.<sent><clb>$
}}}


! Personlege pronomen

{{{
postchunk: ^jeg<prn><pers><p1><mf><sg><nom>$ 
nob fst:  ^jeg/jeg<n><nt><sg><ind>/jeg<n><nt><pl><ind>/jeg<prn><pers><p1><mf><sg><nom>$^./.<sent><clb>$


echo '^jeg<prn><pers><p1><mf><sg><nom>$'|lt-proc -g sme-nob.autogen.bin
jeg
}}}


!!Modes

Kevin har eit script for å lage alle stega i debugginga, alt her er ikkje sjekka (inn).

__TILTAK__

* [[X] Kevin reinskar opp og sjekkar inn
* [[X] sjekk at filene er like som vanlege sme-smi-par
* [[X] fiks: apertium-createmodes.awk: modes/sme-nob-disam.mode seen twice

!!hfst vs bin


{{{
echo "Mii manahit oahpaheaddjiid."|apertium -d. sme-nob-disam|cg-conv -a
"<Mii>"
        "mii" prn ind sg nom
        "mii" prn itg sg nom
        "mii" prn rel sg nom
        "mun" prn pers p1 pl nom
"<manahit>"
        "manahit" vblex tv indic pres p1 pl
        "manahit" vblex tv indic pres p3 pl
        "manahit" vblex tv indic pret p2 sg
        "manahit" vblex tv inf
        "mannat" vblex iv der_h vblex tv indic pres p1 pl
        "mannat" vblex iv der_h vblex tv indic pres p3 pl
        "mannat" vblex iv der_h vblex tv indic pret p2 sg
        "mannat" vblex iv der_h vblex tv inf
"<oahpaheaddjiid>"
        "oahpaheaddji" n nomag sem_hum pl acc
        "oahpaheaddji" n nomag sem_hum pl gen
"<..>"
        ".." sent

Trond: $ echo "Mii manahit oahpaheaddjiid."|apertium -d. sme-nob-pretransfer
^Mii<prn><ind><sg><nom>$ ^manahit<vblex><tv><indic><pres><p1><pl>$ ^oahpaheaddji<n><nomag><sem_hum><pl><acc>$^..<sent>$
 echo "Mii manahit oahpaheaddjiid."|apertium -d. sme-nob
Hva mister lærere.

Lene:
echo "Mii manahit oahpaheaddjiid."|apertium -d. sme-nob-pretransfer
^Mun<prn><pers><p1><pl><nom><@SUBJ→>$ ^manahit<vblex><tv><indic><pres><p1><pl><@+FMAINV>$ ^oahpaheaddji<n><nomag><sem_hum><pl><acc><@←OBJ>$^..<sent>$
Vi mister lærere.

Kevin: $ echo "Mii manahit oahpaheaddjiid."|apertium -d. sme-nob-pretransfer
^Mun<prn><pers><p1><pl><nom><@SUBJ→>$ ^manahit<vblex><tv><indic><pres><p1><pl><@+FMAINV>$ ^oahpaheaddji<n><nomag><sem_hum><pl><acc><@←OBJ>$^..<sent>$

echo "Mii manahit oahpaheaddjiid."|apertium -d. sme-nob-disam|cg-conv -a
"<Mii>"
        "mun" prn pers p1 pl nom SELECT:4019:miiPersRight
        "¬mii" prn ind sg nom SELECT:4019:miiPersRight
        "¬mii" prn itg sg nom SELECT:4019:miiPersRight
        "¬mii" prn rel sg nom SELECT:4019:miiPersRight
"<manahit>"
        "manahit" vblex tv indic pres p1 pl SELECT:4695:VPl1IfMiiLeft MAP:7960:+FMAINV @+FMAINV
        "¬manahit" vblex tv indic pres p3 pl SELECT:4695:VPl1IfMiiLeft
        "¬manahit" vblex tv indic pret p2 sg SELECT:4695:VPl1IfMiiLeft
        "¬manahit" vblex tv inf SELECT:4695:VPl1IfMiiLeft
"<oahpaheaddjiid>"
        "oahpaheaddji" n nomag sem_hum pl acc SELECT:9422:AccTV2
        "¬oahpaheaddji" n nomag sem_hum pl gen SELECT:9422:AccTV2
"<..>"
        ".." sent



Kevin får:
 echo "Mii manahit oahpaheaddjiid."|apertium -d. sme-nob-disam|cg-conv -a
"<Mii>"
        "mun" prn pers p1 pl nom SELECT:4019:miiPersRight
        "¬mii" prn ind sg nom SELECT:4019:miiPersRight
        "¬mii" prn itg sg nom SELECT:4019:miiPersRight
        "¬mii" prn rel sg nom SELECT:4019:miiPersRight
"<manahit>"
        "manahit" vblex tv indic pres p1 pl SELECT:4695:VPl1IfMiiLeft MAP:7960:+FMAINV @+FMAINV
        "¬manahit" vblex tv indic pres p3 pl SELECT:4695:VPl1IfMiiLeft
        "¬manahit" vblex tv indic pret p2 sg SELECT:4695:VPl1IfMiiLeft
        "¬manahit" vblex tv inf SELECT:4695:VPl1IfMiiLeft
"<oahpaheaddjiid>"
        "oahpaheaddji" n nomag sem_hum pl acc SELECT:9422:AccTV2
        "¬oahpaheaddji" n nomag sem_hum pl gen SELECT:9422:AccTV2
"<..>"
        ".." sent



tf4-hsl-m0024:apertium-sme-nob trond$ echo "Mii manahit oahpaheaddjiid."|apertium -d ../../nursery/apertium-sme-smn  sme-smn-disam|cg-conv -a
"<Mii>"
        "mun" prn pers p1 pl nom SELECT:4004:miiPersRight
;        "mii" prn ind sg nom SELECT:4004:miiPersRight
;        "mii" prn itg sg nom SELECT:4004:miiPersRight
;        "mii" prn rel sg nom SELECT:4004:miiPersRight
"<manahit>"
        "manahit" vblex tv indic pres p1 pl @+FMAINV SELECT:4680:VPl1IfMiiLeft MAP:7945:+FMAINV
;        "mannat" ex_vblex ex_iv der_h vblex tv indic pres p1 pl REMOVE:2268:derV
;        "mannat" ex_vblex ex_iv der_h vblex tv indic pres p3 pl REMOVE:2268:derV
;        "mannat" ex_vblex ex_iv der_h vblex tv indic pret p2 sg REMOVE:2268:derV
;        "mannat" ex_vblex ex_iv der_h vblex tv inf REMOVE:2268:derV
;        "manahit" vblex tv indic pres p3 pl SELECT:4680:VPl1IfMiiLeft
;        "manahit" vblex tv indic pret p2 sg SELECT:4680:VPl1IfMiiLeft
;        "manahit" vblex tv inf SELECT:4680:VPl1IfMiiLeft
"<oahpaheaddjiid>"
        "oahpaheaddji" n nomag pl acc SELECT:9407:AccTV2
        "oahpaheaddji" n nomag sem_hum pl acc SELECT:9407:AccTV2
;        "oahpaheaddji" n nomag pl gen SELECT:9407:AccTV2
;        "oahpaheaddji" n nomag sem_hum pl gen SELECT:9407:AccTV2
"<.>"
        "." sent

"<.>"
        "." sent
}}}



!!Feilmeldingar

Kva input er det som gir dette? 
make
Linjene 2131 og 2308 skriv ut <b/> utan pos-attributt.

- Tino er på saka

Feilmeldinga mi kjem ikkje att etter kompilering, no får eg denne:

{{{
tf4-hsl-m0024:apertium-sme-nob trond$ touch apertium-sme-nob.sme-nob.t1x 
tf4-hsl-m0024:apertium-sme-nob trond$ make
apertium-validate-transfer apertium-sme-nob.sme-nob.t1x
apertium-preprocess-transfer apertium-sme-nob.sme-nob.t1x sme-nob.t1x.bin
Warning (3625): Paths to rule 27 blocked by rule 21.
}}}
men rule 27 seier:
{{{
        <rule comment="REGLA: NOM (tl: NOM, VERB)
                   This is a catch-all rule; it's OK that some paths are blocked by previous rules.">
}}}

!!Regresjonstestar
Bruk
{{{
$ t/update-latest 
$ svn diff t
}}}
for å køyra regresjonstestane og lagra resultatet i filer som er lagra i SVN – så får du ein diff med sist gong nokon køyrte testen.