#!/bin/sh
name='diff-daemon'
ver=1.1
#  Copyright (C) 2009 Luke Shumaker
#  
#  This file is part of diff-daemon.
#  
#  diff-daemon is free software; you can redistribute it and/or modify it under
#  the terms of the GNU General Public License as published by the Free Software
#  Foundation; either version 2, or (at your option) any later version.
#  
#  diff-daemon is distributed in the hope that it will be useful, but
#  WITHOUT ANY WARRANTY; without even the implied warranty of
#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
#  See the GNU General Public License for more details.
#  
#  You should have received a copy of the GNU General Public License
#  along with diff-daemon; see the file COPYING.
#  If not, write to the Free Software Foundation,
#  59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.

# count the number of times the char "$1" occurs in string "$2"
# note that the string can't contain any newlines.
chCount() {
	char=$1
	string="$2"
	echo "$string" | tr ':' '\n' | wc -l
	# this returns the correct answer+1
	# this is OK for now, because it is only used for inequality
}

l_common() {
	# If they're the same, just echo one of them
	if [ "$1" = "$2" ]; then
		str="$1"
	else
		# it will be faster if the string with fewer #s is first
		if [ "`chCount ':' "$1"`" -lt "`chCount ':' "$2"`" ]; then
			a0="$1"
			a1="$2"
		else
			a0="$2"
			a1="$1"
		fi
		str=''
		#for int in ${a0//:/: }; do # bash optimized version
		for int in `echo "$a0" | tr ':' ' '`; do
			str="$str`echo ":$a1" | sed -n "s/.*:\($int:\).*/\1/p"`"
		done
	fi
	echo "$str"
}

l_add() {
	str=''
	#for int in ${1//:/: }; do # bash optimized version
	for int in `echo "$1" | tr ':' ' '`; do
		str="$str`expr "$int" + "$2"`:"
	done
	echo "$str"
}

# add a new line with contents $1
print_new() {
	echo "n$1"
}

# insert $1 blank lines
# if $1 is not defined, default to 1
print_blank() {
	echo "b${1-1}"
}

print_copy() {
	if [ -n "$m1" ]; then
		m1="`echo "$m1" | sed 's/:.*//'`"
		if [ "$mi" = '0' ]; then
			mp="${m1}"
		else
			m0="`expr $m1 - $mi`"
			mp="$m0,$m1"
		fi
		if [ -z "`sed -n "$mp p" "$file0"`" ]; then
			print_blank "`expr 1 + $m1 - $m0`"
		else
			echo "c$mp"
		fi
	fi
}

print_uniq() {
	if [ -n "$line" ]; then
		print_new "$line"
	else
		print_blank
	fi
}

matches() {
	grep -n "^$line$" "$file0" | cut -d ':' -f 1 | tr '\n' ':'
}

# main loop

file0="$1"
file1="$2"

i='1'
c=`wc -l "$file1" | cut -d ' ' -f 1`
while [ "$i" -le "$c" ]; do
	line="`sed -n "$i p" "$file1"`"
	
	# it should be simpler to count the `:'s in $m1
	ms="`echo "$m1" | sed 's/:.*//'`"
	#echo "ms=$ms"
	if [ -n "$m1" ] && [ "$m1" = "$ms:" ]; then
		#echo "yay $ms"
		ret1="`expr $ms + 1`"
		if [ "$line" = "`sed -n "$ret1 p" "$file0"`" ]; then
			m1="$ret1:"
			mi=`expr "$mi" + 1`
		else
			print_copy
			m1="`matches`"
			if [ -n "$m1" ]; then
				# start new trend
				mi='0'
			else
				print_uniq
			fi
		fi
	else
		matches="`matches`"
		if [ -n "$matches" ]; then
			ret1=`l_common "$matches" "$(l_add "$m1" '1')"`
			if [ -n "$ret1" ]; then
				# continue trend
				m1="$ret1"
				mi=`expr "$mi" + 1`
			else
				# start new trend
				print_copy
				m1="$matches"
				mi='0'
			fi
		else
			print_copy
			m1=''
			print_uniq
		fi
	fi
	
	i=`expr $i + 1`
done
print_copy