html_md.sh

#!/bin/sh

if [ "$1" = "-d" ]; then
	if [ "$2" = "-html" ]; then
		# delete all .html files
		find . -name "*.ht*" | 
		while read i; 
		do
			rm "$i"; 	
			echo "$i deleted"; 
		done
	fi
	if [ "$2" = "-md" ]; then
		# delete all .md files
		find . -name "*.md" | 
		while read i; 
		do
			rm "$i"; 		
			echo "$i deleted"; 
		done
	fi
fi
if [ "$1" = "-i" ]; then
	# create folder info
	mkdir info;

	find . -name "*.png" | 
	while read i; 
	do		
		echo "$i" >> ./info/list_png.txt; 
	done

	find . -name "*.jpg" | 
	while read i; 
	do		
		echo "$i" >> ./info/list_jpg.txt; 
	done
	
	find . -name "*.md" | 
	while read i; 
	do		
		echo "$i" >> ./info/list_md.txt; 
	done
fi
if [ "$1" = "-w" ]; then
	# download html pages 
	wget -X changelog,portal_css,portal_javascripts,++resource++jquery-ui-themes,anselm-cluster-documentation/icon.jpg -R favicon.ico,pdf.png,logo.png,background.png,application.png,search_icon.png,png.png,sh.png,touch_icon.png,anselm-cluster-documentation/icon.jpg,*js,robots.txt,*xml,RSS,download_icon.png,*zip,*rar,@@*,anselm-cluster-documentation/icon.jpg.1 --mirror --convert-links --adjust-extension --page-requisites  --no-parent https://docs.it4i.cz;
fi
if [ "$1" = "-c" ]; then
	# delete all .md files
	find . -name "*.md" | 
	while read i; 
	do
		rm "$i"; 
		echo "$i deleted"; 
	done
	
	rm -rf info;

	# html -> md
	find . -name "*.ht*" | 
	while read i; 
	do 
		# filtering html
		echo "$i"; 
		printf "\t\tfiltering html files...\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))

		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"
		pandoc -f html -t markdown+pipe_tables-grid_tables "${i%.*}TMP.html" -o "${i%.*}.md"; 
		rm "${i%.*}TMP.html";

		# create 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
		(while read y; 
		do 
			# search and delete according with filter_auto
			sed -e 's/'"$y"'//g' filter_auto > filter_autoTMP;
			cat filter_autoTMP > filter_auto;
		done) < exceptions_filter_auto
	
		# text filtering of html, css, ...
		printf "\t\tautomatic filter...\n"
		(while read y; 
		do 
			# search and delete according with filter_auto
			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' | sed -e 's/^Obsah//g' | awk -v RS='\n\n\n\n\n' 1 > "${i%.*}TMP.md";
			cat "${i%.*}TMP.md" > "${i%.*}.md";
		done) < filter_auto

		# delete temporary files
		rm "${i%.*}TMP.md";		
	done
	find -type f -size -10c | 
	while read i; 
	do
		rm "$i"; 	
		echo "$i deleted"; 
	done
	rm filter_autoTMP
	rm filter_auto
	rm docs.it4i.cz/robots.txt
fi