From 405c98a6a0e017f41f5de9c649a8f6f1b3fc4314 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Thu, 19 Mar 2026 06:33:23 +0100 Subject: contrib: move "update-unicode.sh" script into "tools/" The "update-unicode.sh" script is used to update the unicode data compiled into Git whenever a new version of the Unicode standard has been released. As such, it is a natural part of our developer-facing tooling, and its presence in "contrib/" is misleading. Promote the script into the new "tools/" directory. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- tools/update-unicode/.gitignore | 3 +++ tools/update-unicode/README | 20 ++++++++++++++++++++ tools/update-unicode/update_unicode.sh | 33 +++++++++++++++++++++++++++++++++ 3 files changed, 56 insertions(+) create mode 100644 tools/update-unicode/.gitignore create mode 100644 tools/update-unicode/README create mode 100755 tools/update-unicode/update_unicode.sh (limited to 'tools/update-unicode') diff --git a/tools/update-unicode/.gitignore b/tools/update-unicode/.gitignore new file mode 100644 index 0000000000..b0ebc6aad2 --- /dev/null +++ b/tools/update-unicode/.gitignore @@ -0,0 +1,3 @@ +uniset/ +UnicodeData.txt +EastAsianWidth.txt diff --git a/tools/update-unicode/README b/tools/update-unicode/README new file mode 100644 index 0000000000..151a197041 --- /dev/null +++ b/tools/update-unicode/README @@ -0,0 +1,20 @@ +TL;DR: Run update_unicode.sh after the publication of a new Unicode +standard and commit the resulting unicode-widths.h file. + +The long version +================ + +The Git source code ships the file unicode-widths.h which contains +tables of zero and double width Unicode code points, respectively. +These tables are generated using update_unicode.sh in this directory. +update_unicode.sh itself uses a third-party tool, uniset, to query two +Unicode data files for the interesting code points. + +On first run, update_unicode.sh clones uniset from Github and builds it. +This requires a current-ish version of autoconf (2.69 works per December +2016). + +On each run, update_unicode.sh checks whether more recent Unicode data +files are available from the Unicode consortium, and rebuilds the header +unicode-widths.h with the new data. The new header can then be +committed. diff --git a/tools/update-unicode/update_unicode.sh b/tools/update-unicode/update_unicode.sh new file mode 100755 index 0000000000..aa90865bef --- /dev/null +++ b/tools/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 -- cgit v1.3