aboutsummaryrefslogtreecommitdiff
path: root/contrib
diff options
context:
space:
mode:
authorBeat Bolli <dev+git@drbeat.li>2016-12-14 00:31:39 +0100
committerJunio C Hamano <gitster@pobox.com>2016-12-13 16:12:47 -0800
commitf3eb54920eff356a30df144d50b45a5581e5eb13 (patch)
tree34be6ffc87b5ec37419a587fe00c0a613da39b08 /contrib
parent32c239d1fb23d47aa95cc8a47f99dc25f152021d (diff)
downloadgit-f3eb54920eff356a30df144d50b45a5581e5eb13.tar.gz
git-f3eb54920eff356a30df144d50b45a5581e5eb13.tar.xz
update_unicode.sh: move it into contrib/update-unicode
As it's used only by a tiny minority of the Git developer population, this script does not belong into the main Git source directory. Move it into contrib/ and adjust the paths to account for the new location. Signed-off-by: Beat Bolli <dev+git@drbeat.li> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'contrib')
-rw-r--r--contrib/update-unicode/.gitignore3
-rw-r--r--contrib/update-unicode/README20
-rwxr-xr-xcontrib/update-unicode/update_unicode.sh38
3 files changed, 61 insertions, 0 deletions
diff --git a/contrib/update-unicode/.gitignore b/contrib/update-unicode/.gitignore
new file mode 100644
index 000000000..b0ebc6aad
--- /dev/null
+++ b/contrib/update-unicode/.gitignore
@@ -0,0 +1,3 @@
+uniset/
+UnicodeData.txt
+EastAsianWidth.txt
diff --git a/contrib/update-unicode/README b/contrib/update-unicode/README
new file mode 100644
index 000000000..b9e2fc854
--- /dev/null
+++ b/contrib/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/contrib/update-unicode/update_unicode.sh b/contrib/update-unicode/update_unicode.sh
new file mode 100755
index 000000000..7b901266c
--- /dev/null
+++ b/contrib/update-unicode/update_unicode.sh
@@ -0,0 +1,38 @@
+#!/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
+(
+ if ! test -f UnicodeData.txt; then
+ wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
+ fi &&
+ if ! test -f EastAsianWidth.txt; then
+ wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt
+ fi &&
+ if ! test -d uniset; then
+ git clone https://github.com/depp/uniset.git
+ 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 |
+ grep -v plane)
+ };
+ static const struct interval double_width[] = {
+ $(uniset/uniset --32 eaw:F,W)
+ };
+ EOF
+)