def print_GF(token,ms,mp,fs,fp):
token_id=createGFToken(token,u"A")
if ApertiumLexformGroupProcessor.can_print(token_id):
if ApertiumLexformGroupProcessor.printOnlyTokens:
uniprint(token_id+u" : A ;")
else:
uniprint(u"lin "+token_id+u" = mk4A "+u" ".join([ u"\""+form+u"\"" for form in [ms,fs,mp,fp] ])+u" ;")
ApertiumLexformGroupProcessor.add_to_blacklist(token_id)
def print_GF(lemma,surface):
token_id=createGFToken(lemma,u"Adv")
if ApertiumLexformGroupProcessor.can_print(token_id):
if ApertiumLexformGroupProcessor.printOnlyTokens:
uniprint(token_id+u" : Adv ;")
else:
uniprint(u"lin "+token_id+u" = mkAdv \""+surface+u"\" ;")
ApertiumLexformGroupProcessor.add_to_blacklist(token_id)
def print_GF_genitive( token, sgForm,plForm, sgGenForm, plGenForm):
token_id=createGFToken(token,u"N")
if ApertiumLexformGroupProcessor.can_print(token_id):
if ApertiumLexformGroupProcessor.printOnlyTokens:
uniprint(token_id+u" : N ;")
else:
uniprint(u"lin "+token_id+u" = mkN "+u" ".join([ u"\""+form+u"\"" for form in [sgForm,plForm, sgGenForm, plGenForm] ])+u" ;")
ApertiumLexformGroupProcessor.add_to_blacklist(token_id)
def print_GF_synthetic(lemma,baseform,comparativeForm):
token_id=createGFToken(lemma,u"A")
if ApertiumLexformGroupProcessor.can_print(token_id):
if ApertiumLexformGroupProcessor.printOnlyTokens:
uniprint(token_id+u" : A ;")
else:
uniprint(u"lin "+token_id+" = mkA \""+baseform+"\" \""+comparativeForm+"\" ;")
#don't print an entry with the same token again
ApertiumLexformGroupProcessor.add_to_blacklist(token_id)
def print_GF(token,gender,sgForm,plForm):
genderDict= {u"m":u"masculine", u"f":u"feminine" }
token_id=createGFToken(token,u"N")
if ApertiumLexformGroupProcessor.can_print(token_id):
if ApertiumLexformGroupProcessor.printOnlyTokens:
uniprint(token_id+u" : N ;")
else:
uniprint(u"lin "+token_id+u" = mkN "+u" ".join([ u"\""+form+u"\"" for form in [sgForm, plForm] ] + [genderDict[gender]])+u" ;")
ApertiumLexformGroupProcessor.add_to_blacklist(token_id)
def print_GF(token,gender,surfaceForm):
genderDict= {u"m":u"masculine", u"f":u"feminine" }
token_id=createGFToken(token,u"PN")
if ApertiumLexformGroupProcessor.can_print(token_id):
if ApertiumLexformGroupProcessor.printOnlyTokens:
uniprint(token_id+u" : PN ;")
else:
uniprint(u"lin "+token_id+u" = mkPN \""+surfaceForm+u"\" "+genderDict[gender]+u" ;")
ApertiumLexformGroupProcessor.add_to_blacklist(token_id)
def print_GF(lemma, forms, valency=u"V"):
if not valency in [u"V",u"V2",u"V3",u"VS",u"VV",u"VA",u"VQ"]:
uniprint(u"unknown valency: "+valency,True)
return
token_id=createGFToken(lemma,valency)
if ApertiumLexformGroupProcessor.can_print(token_id):
if ApertiumLexformGroupProcessor.printOnlyTokens:
uniprint(token_id+u" : "+valency+" ;")
else:
uniprint(u"lin "+token_id+u" = "+ ( u"mk"+valency+u" (" if valency != u"V" else u"" ) +u" mkV "+u" ".join([ u"\""+form+u"\"" for form in forms ])+u" "+( u")" if valency != u"V" else u"" )+u" ;")
ApertiumLexformGroupProcessor.add_to_blacklist(token_id)
def print_GF(token,forms,valency=u"V"):
if not valency in [u"V",u"V2",u"V3",u"VS",u"VV",u"VA",u"VQ"]:
uniprint(u"unknown valency: "+valency,True)
return
token_id=createGFToken(token,valency)
if ApertiumLexformGroupProcessor.can_print(token_id):
if ApertiumLexformGroupProcessor.printOnlyTokens:
uniprint(token_id+u" : "+valency+" ;")
else:
addValencyStart=u""
addValencyEnd=u""
if valency != u"V":
addValencyEnd=u")"
if valency == u"V3":
addValencyStart= u"dirdirV3 ("
else:
addValencyStart= u"mk"+valency+u" ("
uniprint(u"lin "+token_id+u" = "+addValencyStart+u" verboV (allforms_67 "+u" ".join([ u"\""+form+u"\"" for form in forms ])+u" ) "+addValencyEnd+u" ;")
ApertiumLexformGroupProcessor.add_to_blacklist(token_id)
cls.valencyDict[entry.lemma].append(entry.valency)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Generates adjective for GF monolingual lexicon')
parser.add_argument('--lang')
parser.add_argument('--category')
parser.add_argument('--bildic_tl_expanded_file')
parser.add_argument('--print_only_tokens',action='store_true')
parser.add_argument('--black_list')
parser.add_argument('--valencies')
parser.add_argument('--no_multiwords',action='store_true')
args = parser.parse_args(sys.argv[1:])
ApertiumLexformGroupProcessor.set_ignore_multiwords(args.no_multiwords)
if args.print_only_tokens:
ApertiumLexformGroupProcessor.printOnlyTokens=True
if args.bildic_tl_expanded_file:
#actual_process bilingual dictionary
#we want as a result a dict() in python which contains, for each TL lemma
#the different SL lemmas which is mapped from in the bilingual dictionary
fileDesc=open(args.bildic_tl_expanded_file,'r')
MultipleLineEntriesProcessor.process(SpaEngBilingualProcessor,BilingualDicLineEntry,fileDesc)
if args.category == "adj":
SpaAdjectivesProcessor.engAdjectivesDict=SpaEngBilingualProcessor.bilingualDictionaryRepresentation
elif args.category == "n":
SpaNounsProcessor.engNounsDict=SpaEngBilingualProcessor.bilingualDictionaryRepresentation
