ICU update to 54 step 3

scripts/euckr_gen.sh

Index: scripts/euckr_gen.sh
diff --git a/scripts/euckr_gen.sh b/scripts/euckr_gen.sh
new file mode 100644
index 0000000000000000000000000000000000000000..ae93c21dc92a0211a70fd04647ad76c5f25f0e0f
--- /dev/null
+++ b/scripts/euckr_gen.sh
@@ -0,0 +1,67 @@
+#!/bin/sh
+# Copyright (c) 2015 The Chromium Authors. All rights reserved.

[jsbell, 2015/01/20 21:47:22]

No (c) per http://www.chromium.org/developers/coding-style#TOC-File-headers

+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+# References:
+#   http://encoding.spec.whatwg.org/#euc-kr
+
+# This script downloads the following file.
+#   https://encoding.spec.whatwg.org/index-euc-kr.txt
+
+function preamble {
+cat <<PREAMBLE
+# ***************************************************************************
+# *
+# *   Copyright (C) 1995-2015, International Business Machines
+# *   Corporation and others.  All Rights Reserved.
+# *
+# *   Generated per the algorithm for EUC-KR
+# *   described at http://encoding.spec.whatwg.org/#euc-kr
+# *
+# ***************************************************************************
+<code_set_name>               "euc-kr-html"
+<mb_cur_max>                  2
+<mb_cur_min>                  1
+<uconv_class>                 "MBCS"
+<subchar>                     \x3F
+<icu:charsetFamily>           "ASCII"
+
+<icu:state>                   0-80, 81-fe:1, ff
+<icu:state>                   40-7e, 80-fe
+
+CHARMAP
+PREAMBLE
+}
+
+function ascii {
+  for i in $(seq 0 127)
+  do
+    printf '<U%04X> \\x%02X |0\n' $i $i
+  done
+}
+
+
+# HKSCS characters are not supported in encoding ( |lead < 0xA1| )
+function euckr {
+  awk '!/^#/ && !/^$/ \
+       { pointer = $1; \
+         ucs = substr($2, 3); \
+         lead = pointer / 190 + 0x81; \
+         trail = $1 % 190 + 0x41; \
+         tag = 0; \
+         printf ("<U%4s> \\x%02X\\x%02X |%d\n", ucs,\
+                 lead,  trail, tag);\
+       }' \
+  index-euc-kr.txt
+}
+
+function unsorted_table {
+  euckr
+}
+
+curl -o index-euc-kr.txt https://encoding.spec.whatwg.org/index-euc-kr.txt
+preamble
+ascii
+unsorted_table | sort -k1  | uniq
+echo 'END CHARMAP'