Commit 31987db9 authored by Koichi Yasuoka's avatar Koichi Yasuoka
Browse files

Tanshi300

parent 21db2ac6
Loading
Loading
Loading
Loading
+25120 −0

File added.

Preview size limit exceeded, changes collapsed.

+445 −0

File changed.

Preview size limit exceeded, changes collapsed.

+1 −0
Original line number Diff line number Diff line
@@ -5175,6 +5175,7 @@
邑,0,0,0,v,動詞,行為,設置,*,*,邑,VERB,*,urbanize
邠,0,0,0,n,名詞,固定物,地名,*,*,邠,PROPN,Case=Loc|NameType=Geo,[place-name]
邢,0,0,0,n,名詞,主体,国名,*,*,邢,PROPN,Case=Loc|NameType=Nat,[country-name]
那,0,0,0,v,副詞,疑問,反語,*,*,那,ADV,*,what
邦,0,0,0,n,名詞,主体,集団,*,*,邦,NOUN,*,country
邪,0,0,0,n,名詞,描写,態度,*,*,邪,NOUN,*,evil
邪,0,0,0,p,助詞,句末,*,*,*,邪,PART,*,[Q]
+1 −0
Original line number Diff line number Diff line
@@ -5175,6 +5175,7 @@
邑 邑 v,動詞,行為,設置 urbanize
邠 邠 n,名詞,固定物,地名 [place-name]
邢 邢 n,名詞,主体,国名 [country-name]
那 那 v,副詞,疑問,反語 what
邦 邦 n,名詞,主体,集団 country
邪 邪 n,名詞,描写,態度 evil
邪 邪 p,助詞,句末,* [Q]
+4 −2
Original line number Diff line number Diff line
@@ -20,7 +20,7 @@ NF==5{
  else
    printf("%s,0,0,0,%s,*,*,%s/%s,*,*,%s\n",$1,$4,$2,$3,$5)|"mc2ud.nawk > dict.gloss.csv";
}' gloss.orig.txt
for F in corpus.pulleyblank.mc corpus.mencius.mc corpus.lunyu.mc corpus.liji.mc corpus.18shilue.mc corpus.chuci.mc corpus.buddha.mc corpus.center.mc
for F in corpus.pulleyblank.mc corpus.mencius.mc corpus.lunyu.mc corpus.liji.mc corpus.18shilue.mc corpus.chuci.mc corpus.tanshi.mc corpus.buddha.mc corpus.center.mc
do ( case $F in
     corpus.mencius.mc) cd ../../ud-kanbun/kanripo/kR1h0001
	cat */*.txt ;;
@@ -32,6 +32,8 @@ do ( case $F in
	cat */*.txt ;;
     corpus.chuci.mc) cd ../../ud-kanbun/kanripo/kR4a0001
	cat */*.txt ;;
     corpus.tanshi.mc) cd ../../ud-kanbun/kanripo/kR4h0169
	cat */*.txt ;;
     corpus.budda.mc) cd ../../ud-kanbun/kanripo
	cat kR6c0023/*/*.txt
	cat kR6f0082/*/*.txt
@@ -107,7 +109,7 @@ do nawk '
}' ../seed_names2/$F | mc2ud.nawk > $F
done

( sed -e /EOS/d -e 's/	/,0,0,0,/' corpus.pulleyblank.mc corpus.mencius.mc corpus.lunyu.mc corpus.liji.mc corpus.18shilue.mc corpus.chuci.mc corpus.buddha.mc corpus.center.mc corpus.KT0.mc corpus.kanjikai.mc corpus.misc.mc
( sed -e /EOS/d -e 's/	/,0,0,0,/' corpus.pulleyblank.mc corpus.mencius.mc corpus.lunyu.mc corpus.liji.mc corpus.18shilue.mc corpus.chuci.mc corpus.tanshi.mc corpus.buddha.mc corpus.center.mc corpus.KT0.mc corpus.kanjikai.mc corpus.misc.mc
  sed 's/,[^,]*,[^,]*,[^,]*$/,*,*,*/' ../seed_names2/KTp2.*.csv ../seed_names2/name.Noun.girei.csv 
) | sort -u | tr , ' ' | nawk '
BEGIN{