clean_translations

#!/bin/bash
# Cleansing script

clean(){
    folder=$(pwd)
    echo "Cleaning files in folder: $folder"
    
    for f in $(find * -type f -maxdepth 0 -name "*.html"); do
        if [ "$f" != "_DONE" ] && [ -n "${f##*gdoc*}" ] && [ -n "${f##*Icon*}" ] && [ -z "${f##*html*}" ]; then
            if grep -q "\[Nid\:" "$f"; then
                echo "Correcting /[Nid:/: $f"
                perl -pi -w -e 's/\[\[Nid\:([0-9]+)\]\]\./\[\[nid\:$1\]\]/g;' "$f"
            fi
            
#            if $(echo "$folder" | grep -qi "german") && grep -q "\&nbsp\;" "$f"; then
#                echo "Correcting / /: $f"
#                perl -pi -w -e 's/\&nbsp\;/ /g;' "$f"            
#            fi
        fi
    done
}

dup(){
    echo "Removing duplicates in folder: $(pwd)"
    ls -lrt | while read item; do
        hold=$(echo "$item" | awk '{print $9}' | sed 's/\.html//g')
        file=$(echo "$item" | awk '{print $9, $10}')
        file=$(echo "$file" | xargs) #remove spaces
        
        #if the file isn't the same name as we would change it to and it's not the _DONE folder or a gdoc file or and empty string...
        [ "$file" != "${hold}.html" ] && [ "$hold" != "_DONE" ] && [ "$file" != "" ] && [ -n "${file##*gdoc*}" ] && [ -n "${file##*Icon*}" ] && [ -z "${file##*html*}" ]  && mv "$file" "${hold}.html" && echo "Duplicate file found: move $file to ${hold}.html"
    done
}

task="$@"

if [ "$task" == "dup" ]; then
    dup
elif [ "$task" == "text" ]; then
    clean
elif [ -z "$task" ]; then
    dup
    clean
else
    echo "Incorrect inputs. Options are:"
    echo "   clean"
    echo "   clean all"
    echo "   clean dup"
    echo "   clean text"
fi