From d945b68b734427a03d114716ff8aeac7998a7c57 Mon Sep 17 00:00:00 2001 From: Daniel Eklöf Date: Sat, 2 May 2020 17:29:00 +0200 Subject: unicode-combine: remove utf8proc dependency We only used utf8proc to try to pre-compose a glyph from a base and combining character. We can do this ourselves by using a pre-compiled table of valid pre-compositions. This table isn't _that_ big, and binary searching it is fast. That is, for a very small amount of code, and not too much extra RO data, we can get rid of the utf8proc dependency. --- scripts/generate-unicode-precompose.sh | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100755 scripts/generate-unicode-precompose.sh (limited to 'scripts') diff --git a/scripts/generate-unicode-precompose.sh b/scripts/generate-unicode-precompose.sh new file mode 100755 index 00000000..830e9379 --- /dev/null +++ b/scripts/generate-unicode-precompose.sh @@ -0,0 +1,8 @@ +#!/usr/bin/sh + +cut - -d ";" -f 1,6 | + grep ";[0-9,A-F]" | grep " " | + sed -e "s/ /, 0x/;s/^/{ 0x/;s/;/, 0x/;s/$/},/" | + sed -e "s,0x\(....\)\([^0-9A-Fa-f]\),0x0\1\2,g" | + (sort -k 3 || sort +2) | + sed -e "s,0x0\(...[0-9A-Fa-f]\),0x\1,g" -- cgit v1.3