summaryrefslogtreecommitdiff
path: root/update_unicode.sh
diff options
context:
space:
mode:
Diffstat (limited to 'update_unicode.sh')
-rwxr-xr-xupdate_unicode.sh40
1 files changed, 40 insertions, 0 deletions
diff --git a/update_unicode.sh b/update_unicode.sh
new file mode 100755
index 0000000000..27af77c7df
--- /dev/null
+++ b/update_unicode.sh
@@ -0,0 +1,40 @@
+#!/bin/sh
+#See http://www.unicode.org/reports/tr44/
+#
+#Me Enclosing_Mark an enclosing combining mark
+#Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
+#Cf Format a format control character
+#
+UNICODEWIDTH_H=../unicode_width.h
+if ! test -d unicode; then
+ mkdir unicode
+fi &&
+( cd unicode &&
+ if ! test -f UnicodeData.txt; then
+ wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
+ fi &&
+ if ! test -f EastAsianWidth.txt; then
+ wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt
+ fi &&
+ if ! test -d uniset; then
+ git clone https://github.com/depp/uniset.git
+ fi &&
+ (
+ cd uniset &&
+ if ! test -x uniset; then
+ autoreconf -i &&
+ ./configure --enable-warnings=-Werror CFLAGS='-O0 -ggdb'
+ fi &&
+ make
+ ) &&
+ UNICODE_DIR=. && export UNICODE_DIR &&
+ cat >$UNICODEWIDTH_H <<-EOF
+ static const struct interval zero_width[] = {
+ $(uniset/uniset --32 cat:Me,Mn,Cf + U+1160..U+11FF - U+00AD |
+ grep -v plane)
+ };
+ static const struct interval double_width[] = {
+ $(uniset/uniset --32 eaw:F,W)
+ };
+ EOF
+)