Alexander/kanji
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases 14 Wiki Activity

various smaller improvements

Browse Source
This commit is contained in:
Alexander Bocken
2021-02-11 21:47:54 +01:00
parent b3f27a5497
commit 12807cfce1
6 changed files with 6803 additions and 4405 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
readings_generator/compounds_script
View File

@ -8,8 +8,6 @@ while read -r line; do
ON="$(hxnormalize -i 0 -x raw_html | hxselect 'table' | awk 'BEGIN {printout=100000000000}; NR==printout+2 {print $0}; /ON reading/ {printout=NR}'| sed 's/<td><b>//; s/<\/b><\/td>//' )"
KUN="$(hxnormalize -i 0 -x raw_html | hxselect 'table' | awk 'BEGIN {printout=100000000000}; NR==printout+2 {print $0}; /KUN reading/ {printout=NR}'| sed 's/<td><b>//; s/<\/b><\/td>//')"
NAN="$(hxnormalize -i 0 -x raw_html | hxselect 'table' | awk 'BEGIN {printout=100000000000}; NR==printout+2 {print $0}; /Nanori reading/ {printout=NR}'| sed 's/<td><b>//; s/<\/b><\/td>//')"
printf '%s\t%s\t%s\t%s\n' "$index" "$ON" "$KUN" "$NAN"
printf '%s\t%s\t%s\t%s\n' "$index" "$ON" "$KUN" "$NAN" | sed 's/ /、/g' | sed 's/、\t/\t/g; s/、$//'
rm raw_html
done<index_kanji
#curl -s http://nihongo.monash.edu/cgi-bin/wwwjdic?1MKJ%B4%D6# | hxnormalize -i 0 -x | hxselect 'table' | awk 'BEGIN {printout=100000000000}; NR==printout+2 {print $0}; /ON reading/ {printout=NR}' | sed 's/<td><b>//; s/<\/b><\/td>//'