summaryrefslogtreecommitdiff
path: root/contrib/update-unicode/update_unicode.sh
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/update-unicode/update_unicode.sh')
-rwxr-xr-xcontrib/update-unicode/update_unicode.sh33
1 files changed, 33 insertions, 0 deletions
diff --git a/contrib/update-unicode/update_unicode.sh b/contrib/update-unicode/update_unicode.sh
new file mode 100755
index 0000000000..aa90865bef
--- /dev/null
+++ b/contrib/update-unicode/update_unicode.sh
@@ -0,0 +1,33 @@
+#!/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
+#
+cd "$(dirname "$0")"
+UNICODEWIDTH_H=$(git rev-parse --show-toplevel)/unicode-width.h
+
+wget -N http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt \
+ http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt &&
+if ! test -d uniset; then
+ git clone https://github.com/depp/uniset.git &&
+ ( cd uniset && git checkout 4b186196dd )
+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)
+};
+static const struct interval double_width[] = {
+ $(uniset/uniset --32 eaw:F,W)
+};
+EOF