html_md.sh

#!/bin/bash

### DOWNLOAD AND CONVERT DOCUMENTATION
# autor: kru0052
# version: 0.4
# change: repair bugs and optimalizations
# bugs: bad formatting tables, bad links for other files, stayed a few html elements, formatting bugs...
###

if [ "$1" = "-t" ]; then
	# testing new function
	
	
fi
if [ "$1" = "-w" ]; then
	# download html pages 
	wget -X pbspro-documentation,changelog,whats-new,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,pdf,*zip,*rar,@@*,anselm-cluster-documentation/icon.jpg.1 --mirror --convert-links --adjust-extension --page-requisites  --no-parent https://docs.it4i.cz;
	
	wget --directory-prefix=./docs.it4i.cz/ http://verif.cs.vsb.cz/aislinn/doc/report.png
	wget --directory-prefix=./docs.it4i.cz/ https://docs.it4i.cz/anselm-cluster-documentation/software/virtualization/virtualization-job-workflow
	wget --directory-prefix=./docs.it4i.cz/ https://docs.it4i.cz/anselm-cluster-documentation/software/omics-master-1/images/fig1.png
	wget --directory-prefix=./docs.it4i.cz/ https://docs.it4i.cz/anselm-cluster-documentation/software/omics-master-1/images/fig2.png
	wget --directory-prefix=./docs.it4i.cz/ https://docs.it4i.cz/anselm-cluster-documentation/software/omics-master-1/images/fig3.png
	wget --directory-prefix=./docs.it4i.cz/ https://docs.it4i.cz/anselm-cluster-documentation/software/omics-master-1/images/fig4.png
	wget --directory-prefix=./docs.it4i.cz/ https://docs.it4i.cz/anselm-cluster-documentation/software/omics-master-1/images/fig5.png
	wget --directory-prefix=./docs.it4i.cz/ https://docs.it4i.cz/anselm-cluster-documentation/software/omics-master-1/images/fig6.png
	
	
fi
if [ "$1" = "-c" ]; then
	### convert html to md
	# erasing the previous transfer
	
	rm -rf converted;
	rm -rf info;
	
	# erasing duplicate files and unwanted files
	(while read i; 
	do		
		if [ -f "$i" ];
		then
			echo "$(tput setaf 9)$i deleted";
		  	rm "$i";
		fi
		
	done) < ./source/list_rm
	
	counter=1
	count=$(find . -name "*.html" -type f | wc -l)
	
	find . -name "*.ht*" | 
	while read i; 
	do 
		# first filtering html 
		echo "$(tput setaf 12)($counter/$count)$(tput setaf 11)$i"; 
		counter=$((counter+1))
		printf "$(tput setaf 15)\t\tfirst filtering 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";

		# second filtering html and css elements...
		printf "\t\tsecond filtering html and css elements...\n"
		sed -e 's/``` /```/' "${i%.*}.md" | sed -e 's/  //' | sed -e 's/<\/div>//g' | sed '/^<div/d' | sed -e 's/<\/span>//' | sed -e 's/^\*\*//' | sed -e 's/\\//g' | sed -e 's/^: //g' | sed -e 's/^Obsah//g' > "${i%.*}TMP.md";
		while read x ; do 
			arg1=`echo "$x" | cut -d"&" -f1 | sed 's:[]\[\^\$\.\*\/\"]:\\\\&:g'`;	
			arg2=`echo "$x" | cut -d"&" -f2 | sed 's:[]\[\^\$\.\*\/\"]:\\\\&:g'`;
	
			sed -e 's/'"$arg1"'/'"$arg2"'/' "${i%.*}TMP.md" > "${i%.*}TMP.TEST.md";
			cat "${i%.*}TMP.TEST.md" > "${i%.*}TMP.md";
		done < ./source/replace 
		
		# repair image...
		printf "\t\trepair images...\n"
		while read x ; do 
			arg1=`echo "$x" | cut -d"&" -f1 | sed 's:[]\[\^\$\.\*\/\"]:\\\\&:g'`;	
			arg2=`echo "$x" | cut -d"&" -f2 | sed 's:[]\[\^\$\.\*\/\"]:\\\\&:g'`;
	
			sed -e 's/'"$arg1"'/'"$arg2"'/' "${i%.*}TMP.md" > "${i%.*}.md";
			cat "${i%.*}.md" > "${i%.*}TMP.md";
		done < ./source/repairIMG
		
		cat "${i%.*}TMP.md" > "${i%.*}.md";
		
		# delete temporary files
		rm "${i%.*}TMP.md";
		rm "${i%.*}TMP.TEST.md";		
	done
	
	# delete empty files
	find -type f -size -10c | 
	while read i; 
	do
		rm "$i"; 	
		echo "$(tput setaf 9)$i deleted"; 
	done

	
	### create new folder and move converted files
	# create folder info and view all files and folder
	mkdir info;
	find ./docs.it4i.cz -name "*.png" -type f > ./info/list_image.txt;
	find ./docs.it4i.cz -name "*.jpg" -type f >> ./info/list_image.txt;
	find ./docs.it4i.cz -name "*.jpeg" -type f >> ./info/list_image.txt;
	find ./docs.it4i.cz -name "*.md" -type f> ./info/list_md.txt; 
	find ./docs.it4i.cz -type d | sort > ./info/list_folder.txt
	
	rm -rf ./converted 
	
	mkdir converted;
	(while read i; 
	do		
		mkdir "./converted/$i";
	done) < ./source/list_folder
	
	# move md files to new folders
	while read a b ; do 
		cp "$a" "./converted/$b"; 
	done < <(paste ./info/list_md.txt ./source/list_md_mv)
		
	# copy jpg and jpeg to new folders
	while read a b ; do 
		cp "$a" "./converted/$b"; 
	done < <(paste ./info/list_image.txt ./source/list_image_mv.txt)
	cp ./docs.it4i.cz/salomon/salomon ./converted/docs.it4i.cz/salomon/salomon
	cp ./docs.it4i.cz/salomon/salomon-2 ./converted/docs.it4i.cz/salomon/salomon-2
	cp ./converted/docs.it4i.cz/salomon/resource-allocation-and-job-execution/fairshare_formula.png ./converted/docs.it4i.cz/anselm-cluster-documentation/resource-allocation-and-job-execution/fairshare_formula.png
	cp ./converted/docs.it4i.cz/salomon/resource-allocation-and-job-execution/job_sort_formula.png ./converted/docs.it4i.cz/anselm-cluster-documentation/resource-allocation-and-job-execution/job_sort_formula.png
	cp ./converted/docs.it4i.cz/salomon/software/debuggers/vtune-amplifier.png ./converted/docs.it4i.cz/anselm-cluster-documentation/software/debuggers/vtune-amplifier.png
	cp ./converted/docs.it4i.cz/salomon/software/debuggers/Snmekobrazovky20160708v12.33.35.png ./converted/docs.it4i.cz/anselm-cluster-documentation/software/debuggers/Snmekobrazovky20160708v12.33.35.png
	cp ./docs.it4i.cz/virtualization-job-workflow ./converted/docs.it4i.cz/anselm-cluster-documentation/software/ 
	
fi