Revised, and initial use of <tw____> pseudo-tags in fix_big5.pl

(will implement it elsewhere later.)

CVS version numbers

chinese/bin/fix_big5.pl: 1.2 -> 1.3 
chinese/bin/tocn.pl: 1.31 -> 1.32 
chinese/bin/totw.pl: 1.33 -> 1.34

3 files changed, 12 insertions, 0 deletions

diff --git a/chinese/bin/fix_big5.pl b/chinese/bin/fix_big5.pl
index f153fb8f8cb..f8a03e9be49 100755
--- a/chinese/bin/fix_big5.pl
+++ b/chinese/bin/fix_big5.pl
@@ -7,3 +7,13 @@ s/^((?:[\x00-\x7F]|(?:[\x80-\xFF].))+[\x80-\xFF]\\)$/$1\\/;
 # while (s%^((?:[\x00-\x7f]|[\x80-\xff].)*)([\x80-\xFF]x)%$1$2%) {}
 while ( s{^((?:[\x00-\x7F]|(?:[\x80-\xFF].))+?)([\x80-\xFF]\{)(?!</protect>)}
 	 {$1<protect>$2</protect>} ) {}
+
+# Note: the following should be automatically generated in the future.
+s/<tw¤ä´©>/[CN:¤ä´©:][HKTW:¤ä«ù:]/g;
+s/<tw(ÀÉ|ÀÉ®×)>/[CN:¤å¥ó:][HKTW:$1:]/g;
+s/<tw¤å¥ó>/[CN:¤åÀÉ:][HKTW:¤å¥ó:]/g;
+s/<tw¸ê°T>/[CN:«H®§:][HKTW:¸ê°T:]/g;
+s/<tw³sµ²>/[CN:Ãì±µ:][HKTW:³sµ²:]/g;
+s/<tw®Ö¤ß>/[CN:®Ö¤ß:][HKTW:®Ö¤ß:]/g;
+s/<tw¸ê®Æ>/[CN:¼Æ¾Ú:][HKTW:¸ê®Æ:]/g;
+s/<tw¶×(¥X|¤J)>/[CN:¾É$1:][HKTW:¶×$1:]/g;
diff --git a/chinese/bin/tocn.pl b/chinese/bin/tocn.pl
index e887e4ba47e..34eb39b7fe8 100755
--- a/chinese/bin/tocn.pl
+++ b/chinese/bin/tocn.pl
@@ -79,6 +79,7 @@ s/ÐÂÎÅȺ×é/ÐÂÎÅ×é/g;
 1 while (s/^((?:[\x00-\x7F]|[\x80-\xFF].)*)Á¬(?=Âç|ϵ)/$1Áª/);
 1 while (s/^((?:[\x00-\x7F]|[\x80-\xFF].)*)Íø·/$1ÍøÂç/);
 1 while (s/^((?:[\x00-\x7F]|[\x80-\xFF].)*)¼Æ»­/$1¼Æ»®/);
+1 while (s/^((?:[\x00-\x7F]|[\x80-\xFF].)*)ËÑÑ°/$1ËÑË÷/);
 1 while (s/^((?:[\x00-\x7F]|[\x80-\xFF].)*)(?:¾­ÓÉ|͸¹ý)/$1ͨ¹ý/);
 
 
diff --git a/chinese/bin/totw.pl b/chinese/bin/totw.pl
index 52cd0314a15..410cab01cdd 100755
--- a/chinese/bin/totw.pl
+++ b/chinese/bin/totw.pl
@@ -56,6 +56,7 @@ s/¸É¤B¤å¥ó/­×¸ÉÀÉ®×/g;
 1 while (s/^((?:[\x00-\x7f]|[\x80-\xff].)*)³q¹L/$1³z¹L/);
 1 while (s/^((?:[\x00-\x7f]|[\x80-\xff].)*)¼e±a/$1¼eÀW/);
 1 while (s/^((?:[\x00-\x7f]|[\x80-\xff].)*)±a¼e/$1ÀW¼e/);
+1 while (s/^((?:[\x00-\x7f]|[\x80-\xff].)*)·j¯Á/$1·j´M/);
 
 if ($sublang eq 'hk') {
     s/§@·~¨t²Î/¾Þ§@¨t²Î/g;