From f3eb54920eff356a30df144d50b45a5581e5eb13 Mon Sep 17 00:00:00 2001 From: Beat Bolli Date: Wed, 14 Dec 2016 00:31:39 +0100 Subject: 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 Signed-off-by: Junio C Hamano diff --git a/.gitignore b/.gitignore index a052419..203703a 100644 --- a/.gitignore +++ b/.gitignore @@ -231,7 +231,6 @@ /config.mak.autogen /config.mak.append /configure -/unicode /tags /TAGS /cscope* diff --git a/contrib/update-unicode/.gitignore b/contrib/update-unicode/.gitignore new file mode 100644 index 0000000..b0ebc6a --- /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 0000000..b9e2fc8 --- /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 0000000..7b90126 --- /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[] = { + $(uniset/uniset --32 eaw:F,W) + }; + EOF +) diff --git a/update_unicode.sh b/update_unicode.sh deleted file mode 100755 index 27af77c..0000000 --- a/update_unicode.sh +++ /dev/null @@ -1,40 +0,0 @@ -#!/bin/sh -#See http://www.unicode.org/reports/tr44/ -# -#Me Enclosing_Mark an enclosing combining mark -#Mn Nonspacing_Mark a nonspacing combining mark (zero advance width) -#Cf Format a format control character -# -UNICODEWIDTH_H=../unicode_width.h -if ! test -d unicode; then - mkdir unicode -fi && -( cd unicode && - if ! test -f UnicodeData.txt; then - wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt - fi && - if ! test -f EastAsianWidth.txt; then - wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt - fi && - if ! test -d uniset; then - git clone https://github.com/depp/uniset.git - fi && - ( - cd uniset && - if ! test -x uniset; then - autoreconf -i && - ./configure --enable-warnings=-Werror CFLAGS='-O0 -ggdb' - fi && - make - ) && - UNICODE_DIR=. && export UNICODE_DIR && - cat >$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 -) -- cgit v0.10.2-6-g49f6