#!/bin/bash

# If this is our first run, save a copy of the system's original hosts file and set to read-only for safety
if [ ! -f ~/hosts-system ]
then
 echo "Saving copy of system's original hosts file..."
 cp /etc/hosts ~/hosts-system
 chmod 444 ~/hosts-system
fi

# Perform work in temporary files
temphosts1=`mktemp`
temphosts2=`mktemp`

# Obtain various hosts files and merge into one
echo "Downloading ad-blocking hosts files..."
wget -nv -O - http://winhelp2002.mvps.org/hosts.txt >> $temphosts1
wget -nv -O - http://hosts-file.net/download/hosts.txt >> $temphosts1
wget -nv -O - http://someonewhocares.org/hosts/hosts >> $temphosts1
wget -nv -O - "http://pgl.yoyo.org/as/serverlist.php?hostformat=hosts&showintro=1&mimetype=plaintext" >> $temphosts1
wget -nv -O - https://raw.githubusercontent.com/jmdugan/blocklists/master/corporations/facebook/all >> $temphosts1

# Do some work on the file:
# 1. Remove MS-DOS carriage returns
# 2. Replace 127.0.0.1 with 0.0.0.0 because then we don't have to wait for the resolver to fail
# 3. Delete all lines that don't begin with 0.0.0.0
# 4. Scrunch extraneous spaces separating address from name into a single tab
# 5. Delete any comments on lines
# 6. Clean up leftover trailing blanks
# 7. Delete any lines ending with the word localhost because we'll obtain that from the original hosts file
# 8. Delete any lines ending with the word .dropbox.com.
# Pass all this through sort with the unique flag to remove duplicates and save the result
echo "Parsing, cleaning, de-duplicating, sorting..."

sed -e 's/\r//' -e 's/127\.0\.0\.1/0\.0\.0\.0/' -e '/^0\.0\.0\.0/!d' -e 's/ \+/\t/' -e 's/#.*$//' -e 's/[ \t]*$//' -e '/localhost$/d' -e '/\.dropbox\.com$/d' < $temphosts1 | sort -u > $temphosts2

# Combine system hosts with adblocks
echo Merging with original system hosts...
echo -e "\n# Ad blocking hosts generated "`date` | cat ~/hosts-system - $temphosts2 > ~/hosts-block

# Clean up temp files and remind user to copy new file
echo "Cleaning up..."
rm $temphosts1 $temphosts2
echo "Done."
cp ~/hosts-block /etc/hosts