The uniset upstream has decided that decimal numbers are The True Way, so
let's convert them back to the usual format that's closer to the U+nnnn
standard.
The generated unicode_widths.h file again looks exactly the same as two
commits ago.
Signed-off-by: Beat Bolli <dev+git@xxxxxxxxx>
---
update_unicode.sh | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/update_unicode.sh b/update_unicode.sh
index e595bf8..d7720d5 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -5,6 +5,12 @@
#Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
#Cf Format a format control character
#
+
+dec_to_hex() {
+ # convert any decimal numbers to 4-digit hex
+ perl -pe 's/(\d+)/sprintf("0x%04X", $1)/ge'
+}
+
UNICODEWIDTH_H=../unicode_width.h
if ! test -d unicode; then
mkdir unicode
@@ -29,7 +35,7 @@ fi &&
make
) &&
UNICODE_DIR=. && export UNICODE_DIR &&
- cat >$UNICODEWIDTH_H <<-EOF
+ dec_to_hex >$UNICODEWIDTH_H <<-EOF
static const struct interval zero_width[] = {
$(uniset/uniset --32 cat:Me,Mn,Cf + U+1160..U+11FF - U+00AD)
};
--
2.7.2