Commit fdd0d47f authored by Koichi Yasuoka's avatar Koichi Yasuoka
Browse files

including corpus.buddha.mc

parent 9f6cef0a
Loading
Loading
Loading
Loading
+0 −0

Empty file added.

+0 −1
Original line number Diff line number Diff line
@@ -1523,7 +1523,6 @@
淈,0,0,0,v,動詞,行為,動作,*,*,淈,VERB,*,*
淖,0,0,0,n,名詞,人,姓氏,*,*,淖,PROPN,NameType=Sur,[surname]
淚,0,0,0,n,名詞,不可譲,身体,*,*,淚/泪,NOUN,*,*
淨,0,0,0,v,動詞,行為,動作,*,*,淨/净,VERB,*,*
淩,0,0,0,n,名詞,不可譲,属性,*,*,淩/凌,NOUN,*,*
淩,0,0,0,v,動詞,行為,動作,*,*,淩/凌,VERB,*,*
淪,0,0,0,v,動詞,行為,動作,*,*,淪/沦,VERB,*,*
+5 −0
Original line number Diff line number Diff line
@@ -2891,6 +2891,10 @@
淇,0,0,0,n,名詞,固定物,地名,*,*,淇,PROPN,Case=Loc|NameType=Geo,[place-name]
淑,0,0,0,v,動詞,描写,態度,*,*,淑,VERB,Degree=Pos,gentle
淡,0,0,0,v,動詞,描写,形質,*,*,淡,VERB,Degree=Pos,thin
净,0,0,0,v,動詞,描写,形質,*,*,淨/净,VERB,Degree=Pos,clean
凈,0,0,0,v,動詞,描写,形質,*,*,淨/净,VERB,Degree=Pos,clean
浄,0,0,0,v,動詞,描写,形質,*,*,淨/净,VERB,Degree=Pos,clean
淨,0,0,0,v,動詞,描写,形質,*,*,淨/净,VERB,Degree=Pos,clean
淫,0,0,0,n,名詞,描写,態度,*,*,淫,NOUN,*,licentious
淫,0,0,0,v,動詞,描写,態度,*,*,淫,VERB,Degree=Pos,excessive
深,0,0,0,v,動詞,描写,量,*,*,深,VERB,Degree=Pos,deep
@@ -3414,6 +3418,7 @@
目,0,0,0,v,動詞,行為,動作,*,*,目,VERB,*,look-at
直,0,0,0,v,副詞,範囲,限定,*,*,直,ADV,*,only
直,0,0,0,v,動詞,描写,形質,*,*,直,VERB,Degree=Pos,straight
相,0,0,0,n,名詞,不可譲,身体,*,*,相,NOUN,*,appearlance
相,0,0,0,n,名詞,人,役割,*,*,相,NOUN,*,chief-minister
相,0,0,0,v,副詞,範囲,共同,*,*,相,ADV,*,each-other
相,0,0,0,v,動詞,行為,交流,*,*,相,VERB,*,assist
+5 −0
Original line number Diff line number Diff line
@@ -2891,6 +2891,10 @@
淇 淇 n,名詞,固定物,地名 [place-name]
淑 淑 v,動詞,描写,態度 gentle
淡 淡 v,動詞,描写,形質 thin
净 淨 净 v,動詞,描写,形質 clean
凈 淨 净 v,動詞,描写,形質 clean
浄 淨 净 v,動詞,描写,形質 clean
淨 淨 净 v,動詞,描写,形質 clean
淫 淫 n,名詞,描写,態度 licentious
淫 淫 v,動詞,描写,態度 excessive
深 深 v,動詞,描写,量 deep
@@ -3414,6 +3418,7 @@
目 目 v,動詞,行為,動作 look-at
直 直 v,副詞,範囲,限定 only
直 直 v,動詞,描写,形質 straight
相 相 n,名詞,不可譲,身体 appearlance
相 相 n,名詞,人,役割 chief-minister
相 相 v,副詞,範囲,共同 each-other
相 相 v,動詞,行為,交流 assist
+6 −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.center.mc
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
do ( case $F in
     corpus.mencius.mc) cd ../../ud-kanbun/kanripo/kR1h0001
	cat */*.txt ;;
@@ -32,6 +32,10 @@ do ( case $F in
	cat */*.txt ;;
     corpus.chuci.mc) cd ../../ud-kanbun/kanripo/kR4a0001
	cat */*.txt ;;
     corpus.budda.mc) cd ../../ud-kanbun/kanripo
	cat kR6c0023/*/*.txt
	cat kR6f0082/*/*.txt
	cat kR6i0076/*/*.txt ;;
     corpus.center.mc) cd ../../ud-kanbun/center-exam
        cat */*.txt ;;
     corpus.pulleyblank.mc) cd ../../ud-kanbun/Pulleyblank
@@ -103,7 +107,7 @@ do nawk '
}' ../seed_names2/$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.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.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{