diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 17:32:43 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 17:32:43 +0000 |
commit | 6bf0a5cb5034a7e684dcc3500e841785237ce2dd (patch) | |
tree | a68f146d7fa01f0134297619fbe7e33db084e0aa /extensions/spellcheck/hunspell/tests/unit/data/suggestiontest/prepare | |
parent | Initial commit. (diff) | |
download | thunderbird-upstream.tar.xz thunderbird-upstream.zip |
Adding upstream version 1:115.7.0.upstream/1%115.7.0upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'extensions/spellcheck/hunspell/tests/unit/data/suggestiontest/prepare')
-rw-r--r-- | extensions/spellcheck/hunspell/tests/unit/data/suggestiontest/prepare | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/extensions/spellcheck/hunspell/tests/unit/data/suggestiontest/prepare b/extensions/spellcheck/hunspell/tests/unit/data/suggestiontest/prepare new file mode 100644 index 0000000000..a72d931b8b --- /dev/null +++ b/extensions/spellcheck/hunspell/tests/unit/data/suggestiontest/prepare @@ -0,0 +1,40 @@ +#!/bin/bash +# Check common misspellings +# input file format: +# word->word1, ... +# Source: http://en.wikipedia.org/wiki/Wikipedia:Lists_of_common_misspellings/For_machines + +hunspell=../../src/tools/hunspell +hlang=${HUNSPELL:-en_US} +alang=${ASPELL:-en_US} +input=${INPUT:-List_of_common_misspellings.txt} + +# remove bad words recognised by Hunspell as good +cat $input | sed 's/[-]>/ /' | $hunspell -d $hlang -1 -L | + +# remove items with dash for Aspell +grep '^[^-]* ' | + +# remove spaces from end of lines +sed 's/ *$//' >$input.1 + +# remove bad words recognised by Aspell as good +cut -f 1 -d ' ' $input.1 | aspell -l $alang --list | +awk 'FILENAME=="-"{a[$1]=1;next}a[$1]{print$0}' - $input.1 | + +# change commas with tabs +sed 's/, */ /g' >$input.2 + +# remove lines with unrecognised suggestions (except suggestion with spaces) +cut -d ' ' -f 2- $input.2 | tr "\t" "\n" | grep -v ' ' >x.1 +cat x.1 | $hunspell -l -d $hlang >x.2 +cat x.1 | aspell -l $alang --list >>x.2 +cat x.2 | awk 'BEGIN{FS="\t"} +FILENAME=="-"{a[$1]=1;next}a[$2]!=1 && a[$3]!=1{print $0}' - $input.2 >$input.3 + +cut -f 1 -d ' ' $input.3 | aspell -l $alang -a | grep -v ^$ | sed -n '2,$p' | +sed 's/^.*: //;s/, / /g' >$input.4 + +cat $input.3 | $hunspell -d $hlang -a -1 | grep -v ^$ | sed -n '2,$p' | +sed 's/^.*: //;s/, / /g' >$input.5 + |