ICU-1997 use uprv_isRuleWhiteSpace for parsing collation rules

X-SVN-Rev: 9354

icu4c/source/data/locales/ja.txt

@@ -434,7 +434,7 @@ ja {
             "&\u309A = \u309A"
 
             // Equaling normal and halfwidth/fullwidth characters
-            "&' '=\u3000" // IDEOGRAPHIC SPACE
+            "&' '='\u3000'" // IDEOGRAPHIC SPACE
             "&'\u0020' = '\uFFE3'" // SPACE
             "&'\u0021' = '\uFF01'" // EXCLAMATION MARK
             "&'\u0022' = '\uFF02'" // QUOTATION MARK

icu4c/source/data/unidata/UCARules.txt

@@ -99,14 +99,14 @@
     =	 ֯
     =	 ֽ
     =	 ׄ
-    =	 ۝
-    =	 ۞
+    =	 '۝'
+    =	 '۞'
     =	 ۟
     =	 ۠
     =	 ۪
     =	 ۫
     =	 ۬
-    =	 ܏
+    =	 '܏'
     =	 ๎
     =	 ༘
     =	 ༙
@@ -117,30 +117,30 @@
     =	 ྆
     =	 ྇
     =	 ࿆
-    =	 ᠋
-    =	 ᠌
-    =	 ᠍
-    =	 ᠎
-    =	 ​
-    =	 ‌
-    =	 ‍
-    =	 ‎
-    =	 ‏
-    =	 ‪
-    =	 ‫
-    =	 ‬
-    =	 ‭
-    =	 ‮
-    =	 
-    =	 
-    =	 
-    =	 
-    =	 
-    =	 
-    =	 
-    =	 
-    =	 
-    =	 
+    =	 '᠋'
+    =	 '᠌'
+    =	 '᠍'
+    =	 '᠎'
+    =	 '​'
+    =	 '‌'
+    =	 '‍'
+    =	 '‎'
+    =	 '‏'
+    =	 '‪'
+    =	 '‫'
+    =	 '‬'
+    =	 '‭'
+    =	 '‮'
+    =	 ''
+    =	 ''
+    =	 ''
+    =	 ''
+    =	 ''
+    =	 ''
+    =	 ''
+    =	 ''
+    =	 ''
+    =	 ''
     =	 𝅥
     =	 𝅦
     =	 𝅧
@@ -555,23 +555,23 @@
  <	 '\u000C'
  <	 '\u000D'
  <	 '\u0085'
- <	 

- <	 

+ <	 '\u2028'
+ <	 '
'
  <	 '\u0020'
-   <<<	 　
-   <<<	  
-    =	  
-    =	  
-    =	  
-    =	  
-    =	  
-    =	  
-    =	  
-   <<<	  
-    =	  
-    =	  
- <	  
- <	 ـ
+   <<<	 '　'
+   <<<	 ' '
+    =	 ' '
+    =	 ' '
+    =	 ' '
+    =	 ' '
+    =	 ' '
+    =	 ' '
+    =	 ' '
+   <<<	 ' '
+    =	 ' '
+    =	 ' '
+ <	 ' '
+ <	 'ـ'
  <	 '`'
    <<<	 ｀
  <	 ´

icu4c/source/i18n/ucol_tok.cpp

@@ -23,6 +23,7 @@
  
 #include "ucol_tok.h"
 #include "cmemory.h"
+#include "uprops.h"
 
 U_CDECL_BEGIN
 static int32_t U_EXPORT2 U_CALLCONV
@@ -712,6 +713,7 @@ ucol_tok_parseNextToken(UColTokenParser *src,
           }
       }
     }else {
+      if(!uprv_isRuleWhiteSpace(ch)) {
         /* Sets the strength for this entry */
         switch (ch) {
           case 0x003D/*'='*/ : 
@@ -850,13 +852,6 @@ ucol_tok_parseNextToken(UColTokenParser *src,
               }
             }
             break;
-        /* Ignore the white spaces */
-        case 0x0009/*'\t'*/:
-        case 0x000C/*'\f'*/:
-        case 0x000D/*'\r'*/:
-        case 0x000A/*'\n'*/:
-        case 0x0020/*' '*/:  
-          break; /* skip whitespace TODO use Unicode */
 		  case 0x0021/*! skip java thai modifier reordering*/:
 			  break; 
           case 0x002F/*'/'*/:
@@ -981,6 +976,7 @@ ucol_tok_parseNextToken(UColTokenParser *src,
             break;
           }         
        }
+    }
 
     if(wasInQuote) {
       if(ch != 0x27) {