forgejo/build/update-locales.sh
wxiaoguang d72462dae6
Improve update-locales script and fix locale processing bug (#23240)
The locales of Gitea has been broken for long time, till now, it's still
not fully fixed.

One of the root problems is that the `ini` library is quite quirky and
the `update-locales` script doesn't work well for all cases.


This PR fixes the `update-locales` script to make it satisfy `ini`
library and the crowdin.

See the comments for more details.

The `locale_zh-CN.ini` is an example, it comes from crowdin and is
processed by the new `update-locales.sh`. Especially see the `feed_of`:
https://github.com/go-gitea/gitea/pull/23240/files#diff-321f6ca4eae1096eba230e93c4740f9903708afe8d79cf2e57f4299786c4528bR268
2023-03-02 12:33:36 -06:00

58 lines
1.9 KiB
Bash
Executable file

#!/bin/bash
set -e
SED=sed
if [[ $OSTYPE == 'darwin'* ]]; then
# for macOS developers, use "brew install gnu-sed"
SED=gsed
fi
if [ ! -f ./options/locale/locale_en-US.ini ]; then
echo "please run this script in the root directory of the project"
exit 1
fi
mv ./options/locale/locale_en-US.ini ./options/
# the "ini" library for locale has many quirks
# * `a="xx"` gets `xx` (no quote)
# * `a=x\"y` gets `x\"y` (no unescaping)
# * `a="x\"y"` gets `"x\"y"` (no unescaping, the quotes are still there)
# * `a='x\"y'` gets `x\"y` (no unescaping, no quote)
# * `a="foo` gets `"foo` (although the quote is not closed)
# * 'a=`foo`' works like single-quote
# crowdin needs the strings to be quoted correctly and doesn't like incomplete quotes
# crowdin always outputs quoted strings if there are quotes in the strings.
# this script helps to unquote the crowdin outputs for the quirky ini library
# * find all `key="...\"..."` lines
# * remove the leading quote
# * remove the trailing quote
# * unescape the quotes
# * eg: key="...\"..." => key=..."...
$SED -i -r -e '/^[-.A-Za-z0-9_]+[ ]*=[ ]*".*"$/ {
s/^([-.A-Za-z0-9_]+)[ ]*=[ ]*"/\1=/
s/"$//
s/\\"/"/g
}' ./options/locale/*.ini
# * if the escaped line is incomplete like `key="...` or `key=..."`, quote it with backticks
# * eg: key="... => key=`"...`
# * eg: key=..." => key=`..."`
$SED -i -r -e 's/^([-.A-Za-z0-9_]+)[ ]*=[ ]*(".*[^"])$/\1=`\2`/' ./options/locale/*.ini
$SED -i -r -e 's/^([-.A-Za-z0-9_]+)[ ]*=[ ]*([^"].*")$/\1=`\2`/' ./options/locale/*.ini
# Remove translation under 25% of en_us
baselines=$(wc -l "./options/locale_en-US.ini" | cut -d" " -f1)
baselines=$((baselines / 4))
for filename in ./options/locale/*.ini; do
lines=$(wc -l "$filename" | cut -d" " -f1)
if [ $lines -lt $baselines ]; then
echo "Removing $filename: $lines/$baselines"
rm "$filename"
fi
done
mv ./options/locale_en-US.ini ./options/locale/