about summary refs log tree commit diff
path: root/contrib/update-unicode/update_unicode.sh
diff options
context:
space:
mode:
authorVincent Ambo <Vincent Ambo>2020-01-11T23·36+0000
committerVincent Ambo <Vincent Ambo>2020-01-11T23·36+0000
commit1b593e1ea4d2af0f6444d9a7788d5d99abd6fde5 (patch)
treee3accb9beed5c4c1b5a05c99db71ab2841f0ed04 /contrib/update-unicode/update_unicode.sh
Squashed 'third_party/git/' content from commit cb71568594
git-subtree-dir: third_party/git
git-subtree-split: cb715685942260375e1eb8153b0768a376e4ece7
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 000000000000..aa90865befa4
--- /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