diff --git a/html_md.sh b/html_md.sh index 93526f9f62a430dab11027c5cc9ef33b3d28dbaa..8c9f699df9358499f18114dd76a1f92fe3afa13e 100755 --- a/html_md.sh +++ b/html_md.sh @@ -84,12 +84,12 @@ if [ "$1" = "-c" ]; then echo "$i"; printf "\t\tfiltering html files...\n"; - HEAD=$(cat "$i" | grep -n -m1 '<h1' |cut -f1 -d: | tr --delete '\n') - END=$(cat "$i" | grep -n -m1 '<!-- <div tal:content=' |cut -f1 -d: | tr --delete '\n') - LAST=$(cat "$i" | wc -l | tr --delete '\n') + HEAD=$(grep -n -m1 '<h1' "$i" |cut -f1 -d: | tr --delete '\n') + END=$(grep -n -m1 '<!-- <div tal:content=' "$i" |cut -f1 -d: | tr --delete '\n') + LAST=$(wc -l "$i" | cut -f1 -d' ') DOWN=$((LAST-END+2)) - cat "$i" | sed '1,'"$((HEAD-1))"'d' | sed -n -e :a -e '1,'"$DOWN"'!{P;N;D;};N;ba' > "${i%.*}TMP.html" + sed '1,'"$((HEAD-1))"'d' "$i" | sed -n -e :a -e '1,'"$DOWN"'!{P;N;D;};N;ba' > "${i%.*}TMP.html" # converted .html to .md printf "\t\t.html -> .md\n" @@ -100,36 +100,33 @@ if [ "$1" = "-c" ]; then echo "${i%.*}" >> ./info/files_md.txt; # create filter_auto - cat "${i%.*}.md" | grep -o -P '(?<={).*(?=})' | sort -u | sed '/{/d' | sed '/\$/d' >> filter_auto; + grep -o -P '(?<={).*(?=})' "${i%.*}.md" | sort -u | sed '/{/d' | sed '/\$/d' >> filter_auto; sort -u filter_auto -o filter_auto; # exceptions filter_auto - cat exceptions_filter_auto | - while read y; + (while read y; do # search and delete according with filter_auto - cat filter_auto | sed -e 's/'"$y"'//g' > filter_autoTMP; + sed -e 's/'"$y"'//g' filter_auto > filter_autoTMP; cat filter_autoTMP > filter_auto; - done + done) < exceptions_filter_auto # text filtering of html, css, ... printf "\t\tautomatic filter...\n" - cat filter_auto | - while read y; + (while read y; do # search and delete according with filter_auto - cat "${i%.*}.md" | sed -e 's/{'"$y"'}//g' | sed -e 's/\\//g' | sed -e 's/^Q//g' | sed -e 's/: //g' | sed -e 's/<\/div>//g' | sed '/^<div/d' | awk -v RS='\n\n\n\n\n' 1 > "${i%.*}TMP.md"; + sed -e 's/{'"$y"'}//g' "${i%.*}.md" | sed -e 's/\\//g' | sed -e 's/^Q//g' | sed -e 's/: //g' | sed -e 's/<\/div>//g' | sed '/^<div/d' | awk -v RS='\n\n\n\n\n' 1 > "${i%.*}TMP.md"; cat "${i%.*}TMP.md" > "${i%.*}.md"; - done + done) < filter_auto printf "\t\tother filter...\n" - cat filter_other | - while read a; + (while read a; do # search and delete according with filter_other - cat "${i%.*}.md" | sed -e 's/'"$a"'//g' > "${i%.*}TMP.md"; + sed -e 's/'"$a"'//g' "${i%.*}.md" > "${i%.*}TMP.md"; cat "${i%.*}TMP.md" > "${i%.*}.md"; - done + done) < filter_other # delete temporary files rm "${i%.*}TMP.md";