about summary refs log tree commit diff
path: root/contrib/update-unicode
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/update-unicode')
-rw-r--r--contrib/update-unicode/.gitignore3
-rw-r--r--contrib/update-unicode/README20
-rwxr-xr-xcontrib/update-unicode/update_unicode.sh33
3 files changed, 56 insertions, 0 deletions
diff --git a/contrib/update-unicode/.gitignore b/contrib/update-unicode/.gitignore
new file mode 100644
index 000000000000..b0ebc6aad214
--- /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 000000000000..151a1970419f
--- /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 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