Update CJK converters and their generating scripts

source/data/mappings/big5-html.ucm

 # ***************************************************************************
 # *
 # *   Copyright (C) 1995-2014, International Business Machines
 # *   Corporation and others.  All Rights Reserved.
 # *
 # *   Generated per the algorithm for Big5
 # *   described at http://encoding.spec.whatwg.org/#big5
 # *
 # ***************************************************************************
 <code_set_name>               "big5-html"
 <char_name_mask>              "AXXXX"
 <mb_cur_max>                  2
 <mb_cur_min>                  1
 <uconv_class>                 "MBCS"
 <subchar>                     \x3F
 <icu:charsetFamily>           "ASCII"
 
 # 'p' is for the range that may produce non-BMP code points.
+# 'i' is to make the code range illegal.
+# Big5 has a lot of small holes in the 2nd byte. If it's in the ASCII range,
+# the 2nd byte has to be added back to the stream to be compliant to the
+# encoding spec. Each state adds 1kB in the data size.
 # See http://userguide.icu-project.org/conversion/data.
-<icu:state>                   0-7f, 87-fe:1, 87-a0:2, c8:2, fa-fe:2
+<icu:state>                   0-7f, a1-fe:1, 87-a0:2, c8:2, fa-fe:2, 87:3, 89:4, 8a:5, 8b:6, 8d:7, 9b:8, 9f:9, a0:a
 <icu:state>                   40-7e, a1-fe
 <icu:state>                   40-7e.p, a1-fe.p
+<icu:state>                   40-7e.p, a1-fe.p, 66.i
+<icu:state>                   40-7e.p, a1-fe.p, 42.i, 44.i, 45.i, 4a-4b.i
+<icu:state>                   40-7e.p, a1-fe.p, 42.i, 63.i, 75.i
+<icu:state>                   40-7e.p, a1-fe.p, 54.i
+<icu:state>                   40-7e.p, a1-fe.p, 41.i
+<icu:state>                   40-7e.p, a1-fe.p, 61.i
+<icu:state>                   40-7e.p, a1-fe.p, 4e.i
+<icu:state>                   40-7e.p, a1-fe.p, 54.i, 57.i, 5a.i, 62.i, 72.i
 
 CHARMAP
 <U0000> \x00 |0
 <U0001> \x01 |0
 <U0002> \x02 |0
 <U0003> \x03 |0
 <U0004> \x04 |0
 <U0005> \x05 |0
 <U0006> \x06 |0
 <U0007> \x07 |0
@@ skipping 18705 matching lines @@
 <U2F840> \xA0\x47 |3
 <U2F878> \x8B\xC3 |3
 <U2F894> \xFC\x48 |0
 <U2F8A6> \xFC\x77 |0
 <U2F8CD> \x9C\x52 |3
 <U2F994> \x8E\xFD |3
 <U2F9B2> \x8F\xA8 |3
 <U2F9BC> \x95\x7A |3
 <U2F9D4> \x8F\xF0 |3
 END CHARMAP