You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2013/10/20 11:53:43 UTC

svn commit: r1533865 - in /lucene/dev/branches/lucene4956/lucene/analysis/arirang/src: data/dictionary.dic resources/org/apache/lucene/analysis/ko/dic/dictionary.dic test/org/apache/lucene/analysis/ko/wiki_results.txt

Author: rmuir
Date: Sun Oct 20 09:53:40 2013
New Revision: 1533865

URL: http://svn.apache.org/r1533865
Log:
LUCENE-4956: fix malformed entries

Modified:
    lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/data/dictionary.dic
    lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/resources/org/apache/lucene/analysis/ko/dic/dictionary.dic
    lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/test/org/apache/lucene/analysis/ko/wiki_results.txt

Modified: lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/data/dictionary.dic
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/data/dictionary.dic?rev=1533865&r1=1533864&r2=1533865&view=diff
==============================================================================
--- lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/data/dictionary.dic (original)
+++ lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/data/dictionary.dic Sun Oct 20 09:53:40 2013
@@ -231,9 +231,9 @@ WORD,NVZDBIPSCC
 가사리,100000000X
 가산,100110000X
 가살스럽,010000000B
-가상,10111000X
+가상,101110000X
 가상극,100000000X
-가석방,10011000X
+가석방,100110000X
 가선,100100000X
 가설,100110000X
 가설적,100000000X
@@ -1156,7 +1156,7 @@ WORD,NVZDBIPSCC
 개척,100110000X
 개천,100000000X
 개체,100100000X
-개최,1001`0000X
+개최,100110000X
 개축,100110000X
 개칭,100110000X
 개코같,010000000X
@@ -1217,7 +1217,7 @@ WORD,NVZDBIPSCC
 객회,100000000X
 갤러리,100000000X
 ê°­,100000000X
-갯가,100000000
+갯가,100000000X
 갯발,100000000X
 갯벌,100000000X
 ê°±,100000000X
@@ -1348,8 +1348,8 @@ WORD,NVZDBIPSCC
 거스러미,100000000X
 거스르,010000000L
 거스름,100000000X
-거슬러올라가,0100000000X
-거슬리,0100000000X
+거슬러올라가,010000000X
+거슬리,010000000X
 거슴츠레,001100000X
 거시,100100000X
 거시적,100000000X
@@ -3152,7 +3152,7 @@ WORD,NVZDBIPSCC
 교침,100000000X
 교탁,100000000X
 교태,100100000X
-교태부리,0100000000X
+교태부리,010000000X
 교통,100100000X
 교파,100000000X
 교편,100000000X
@@ -3319,7 +3319,7 @@ WORD,NVZDBIPSCC
 구슬프,010000000X
 구습,100000000X
 구승,100110000X
-구시,100100000
+구시,100100000X
 구시렁거리,010000000X
 구시렁대,010000000X
 구식,100000000X
@@ -5320,7 +5320,7 @@ WORD,NVZDBIPSCC
 나라지,010000000X
 나라타주,100000000X
 나락,100000000X
-나란하,0100000000X
+나란하,010000000X
 나랏일,100000000X
 나래,100110000X
 나루,100000000X
@@ -27121,7 +27121,7 @@ WORD,NVZDBIPSCC
 질러오,010000000X
 질료,100000000X
 질리,010000000X
-질문,10011000X
+질문,100110000X
 질박,100100000X
 질벅,100100000X
 질벅거리,010000000X
@@ -27817,7 +27817,7 @@ WORD,NVZDBIPSCC
 창궐,100100000X
 창극,100000000X
 창녀,100000000X
-창단,1001100000X
+창단,100110000X
 창달,100100000X
 창당,100100000X
 창덕,100100000X
@@ -28383,7 +28383,7 @@ WORD,NVZDBIPSCC
 청장,100100000X
 청장년,100000000X
 청정,100100000X
-청정심,1000100000X
+청정심,100010000X
 청주,100000000X
 청죽,100000000X
 청중,100000000X
@@ -28415,7 +28415,7 @@ WORD,NVZDBIPSCC
 ì²´ê²°,100110000X
 ì²´ê²½,100100000X
 체계,100100000X
-체계화,1001100000X
+체계화,100110000X
 ì²´ê³ ,100110000X
 ì²´ê³µ,100100000X
 체구,100000000X
@@ -28669,7 +28669,7 @@ WORD,NVZDBIPSCC
 촌평,100100000X
 촐랑거리,010000000X
 촐랑대,010000000X
-촐랑이,1100000000X
+촐랑이,110000000X
 촐싹거리,010000000X
 촐싹대,010000000X
 촐싹이,010000000X
@@ -28955,7 +28955,7 @@ WORD,NVZDBIPSCC
 축전,100110000X
 축전기,100000000X
 축제,100100000X
-축조,100``0000X
+축조,100110000X
 축지,100100000X
 축척,100100000X
 축축,100100000X
@@ -28970,7 +28970,7 @@ WORD,NVZDBIPSCC
 춘궁기,100000000X
 춘당,100000000X
 춘란,100000000X
-춘몽,00000000X
+춘몽,100000000X
 춘분,100000000X
 춘삼월,100000000X
 춘심,100000000X
@@ -28983,7 +28983,7 @@ WORD,NVZDBIPSCC
 춘화,100000000X
 출가,100100000X
 출가외인,100000000X
-출간,100``0000X
+출간,100110000X
 출감,100110000X
 출강,100100000X
 출격,100100000X
@@ -28992,7 +28992,7 @@ WORD,NVZDBIPSCC
 출고,100110000X
 출구,100100000X
 출국,100100000X
-출군,100`00000X
+출군,100100000X
 출근,100100000X
 출근부,100000000X
 출금,100100000X
@@ -30503,7 +30503,7 @@ WORD,NVZDBIPSCC
 토지,100000000X
 토질,100000000X
 토착,100100000X
-토착화,1001`0000X
+토착화,100110000X
 토치카,100000000X
 토큰,100000000X
 토탄,100000000X
@@ -31327,7 +31327,7 @@ WORD,NVZDBIPSCC
 퍼레이드,100000000X
 퍼마시,010000000X
 퍼먹,010000000X
-퍼벌하,0101000000X
+퍼벌하,010100000X
 퍼붓,010000000S
 퍼서석하,010000000X
 퍼석하,010000000X

Modified: lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/resources/org/apache/lucene/analysis/ko/dic/dictionary.dic
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/resources/org/apache/lucene/analysis/ko/dic/dictionary.dic?rev=1533865&r1=1533864&r2=1533865&view=diff
==============================================================================
--- lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/resources/org/apache/lucene/analysis/ko/dic/dictionary.dic (original)
+++ lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/resources/org/apache/lucene/analysis/ko/dic/dictionary.dic Sun Oct 20 09:53:40 2013
@@ -231,9 +231,9 @@ WORD,NVZDBIPSCC
 가사리,100000000X
 가산,100110000X
 가살스럽,010000000B
-가상,10111000X
+가상,101110000X
 가상극,100000000X
-가석방,10011000X
+가석방,100110000X
 가선,100100000X
 가설,100110000X
 가설적,100000000X
@@ -1156,7 +1156,7 @@ WORD,NVZDBIPSCC
 개척,100110000X
 개천,100000000X
 개체,100100000X
-개최,1001`0000X
+개최,100110000X
 개축,100110000X
 개칭,100110000X
 개코같,010000000X
@@ -1217,7 +1217,7 @@ WORD,NVZDBIPSCC
 객회,100000000X
 갤러리,100000000X
 ê°­,100000000X
-갯가,100000000
+갯가,100000000X
 갯발,100000000X
 갯벌,100000000X
 ê°±,100000000X
@@ -1348,8 +1348,8 @@ WORD,NVZDBIPSCC
 거스러미,100000000X
 거스르,010000000L
 거스름,100000000X
-거슬러올라가,0100000000X
-거슬리,0100000000X
+거슬러올라가,010000000X
+거슬리,010000000X
 거슴츠레,001100000X
 거시,100100000X
 거시적,100000000X
@@ -3152,7 +3152,7 @@ WORD,NVZDBIPSCC
 교침,100000000X
 교탁,100000000X
 교태,100100000X
-교태부리,0100000000X
+교태부리,010000000X
 교통,100100000X
 교파,100000000X
 교편,100000000X
@@ -3319,7 +3319,7 @@ WORD,NVZDBIPSCC
 구슬프,010000000X
 구습,100000000X
 구승,100110000X
-구시,100100000
+구시,100100000X
 구시렁거리,010000000X
 구시렁대,010000000X
 구식,100000000X
@@ -5320,7 +5320,7 @@ WORD,NVZDBIPSCC
 나라지,010000000X
 나라타주,100000000X
 나락,100000000X
-나란하,0100000000X
+나란하,010000000X
 나랏일,100000000X
 나래,100110000X
 나루,100000000X
@@ -27121,7 +27121,7 @@ WORD,NVZDBIPSCC
 질러오,010000000X
 질료,100000000X
 질리,010000000X
-질문,10011000X
+질문,100110000X
 질박,100100000X
 질벅,100100000X
 질벅거리,010000000X
@@ -27817,7 +27817,7 @@ WORD,NVZDBIPSCC
 창궐,100100000X
 창극,100000000X
 창녀,100000000X
-창단,1001100000X
+창단,100110000X
 창달,100100000X
 창당,100100000X
 창덕,100100000X
@@ -28383,7 +28383,7 @@ WORD,NVZDBIPSCC
 청장,100100000X
 청장년,100000000X
 청정,100100000X
-청정심,1000100000X
+청정심,100010000X
 청주,100000000X
 청죽,100000000X
 청중,100000000X
@@ -28415,7 +28415,7 @@ WORD,NVZDBIPSCC
 ì²´ê²°,100110000X
 ì²´ê²½,100100000X
 체계,100100000X
-체계화,1001100000X
+체계화,100110000X
 ì²´ê³ ,100110000X
 ì²´ê³µ,100100000X
 체구,100000000X
@@ -28669,7 +28669,7 @@ WORD,NVZDBIPSCC
 촌평,100100000X
 촐랑거리,010000000X
 촐랑대,010000000X
-촐랑이,1100000000X
+촐랑이,110000000X
 촐싹거리,010000000X
 촐싹대,010000000X
 촐싹이,010000000X
@@ -28955,7 +28955,7 @@ WORD,NVZDBIPSCC
 축전,100110000X
 축전기,100000000X
 축제,100100000X
-축조,100``0000X
+축조,100110000X
 축지,100100000X
 축척,100100000X
 축축,100100000X
@@ -28970,7 +28970,7 @@ WORD,NVZDBIPSCC
 춘궁기,100000000X
 춘당,100000000X
 춘란,100000000X
-춘몽,00000000X
+춘몽,100000000X
 춘분,100000000X
 춘삼월,100000000X
 춘심,100000000X
@@ -28983,7 +28983,7 @@ WORD,NVZDBIPSCC
 춘화,100000000X
 출가,100100000X
 출가외인,100000000X
-출간,100``0000X
+출간,100110000X
 출감,100110000X
 출강,100100000X
 출격,100100000X
@@ -28992,7 +28992,7 @@ WORD,NVZDBIPSCC
 출고,100110000X
 출구,100100000X
 출국,100100000X
-출군,100`00000X
+출군,100100000X
 출근,100100000X
 출근부,100000000X
 출금,100100000X
@@ -30503,7 +30503,7 @@ WORD,NVZDBIPSCC
 토지,100000000X
 토질,100000000X
 토착,100100000X
-토착화,1001`0000X
+토착화,100110000X
 토치카,100000000X
 토큰,100000000X
 토탄,100000000X
@@ -31327,7 +31327,7 @@ WORD,NVZDBIPSCC
 퍼레이드,100000000X
 퍼마시,010000000X
 퍼먹,010000000X
-퍼벌하,0101000000X
+퍼벌하,010100000X
 퍼붓,010000000S
 퍼서석하,010000000X
 퍼석하,010000000X

Modified: lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/test/org/apache/lucene/analysis/ko/wiki_results.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/test/org/apache/lucene/analysis/ko/wiki_results.txt?rev=1533865&r1=1533864&r2=1533865&view=diff
==============================================================================
Binary files - no diff available.