diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | contrib/update-unicode/.gitignore | 3 | ||||
| -rw-r--r-- | contrib/update-unicode/README | 20 | ||||
| -rwxr-xr-x | contrib/update-unicode/update_unicode.sh (renamed from update_unicode.sh) | 8 |
4 files changed, 26 insertions, 6 deletions
@@ -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/update_unicode.sh b/contrib/update-unicode/update_unicode.sh index 27af77c..7b90126 100755 --- a/update_unicode.sh +++ b/contrib/update-unicode/update_unicode.sh @@ -5,11 +5,9 @@ #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 && +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 && |