#!/bin/bash

if [ $# -lt 3 ]
then
	echo "LgEval ldiff: List Files with Common Errors"
	echo "Copyright (c) R. Zanibbi, H. Mouchere, 2012-2014"
	echo ""
	echo "Usage: ldiff [-NESC^] outputPattern targetPattern <files>"
	echo ""
	echo "Create a list of files that contain errors on label graph"
	echo "nodes or edges matching the provided patterns (egrep-format"
	echo "regular expressions). Matching files are written on standard output."
	echo ""
	echo "*Note: the pattern 'any' will match any label."
	echo ""
	echo "A single flag list token indicates whether to limit matches to"
	echo "(N)ode label errors, (E)dge label errors, and/or files with"
	echo "(S)egmentation errors or only (C)orrect segmentations. Including"
	echo "^ in the flag list token will return files that do not match the"
	echo "passed patterns."
	exit 0
fi

# By default, return files matching the given patterns.
FLIST="-l"

# Create initial list of all .diff files.
CFILES=""
FLAGS=""

if [[ $1 == -* ]]
then
	# Grab flag string and shift.
	FLAGS=$1
	shift
fi

# Grad the patterns; shift to file list.
OUTP=$1
TARP=$2
shift
shift

# Take CFILES (current files) as all passed .diff files.
CFILES="$@"


# Indicate if we want the complement of a match.
if [[ $FLAGS == *^* ]]
then
	FLIST="-L"
fi

# Note that segment error/correct seg are exclusive.
if [[ $FLAGS == *S* ]]
then
	CFILES=`grep -l "^*S" $@`
elif [[ $FLAGS == *C* ]]
then	
	# -L flag selects inverse of the pattern ('negates' it)
	CFILES=`grep -L "^*S" $@`
fi

# one or more non-comma characters: reg expression for 'any label' (*)
# Create the pattern string to use with grep, then run the filter and
# obtain the list of matching files.
ANYLABEL="[^,][^,]*"
MID=",1.0,:vs:,"

OUTLABEL=$ANYLABEL
TARLABEL=$ANYLABEL
if [ "$OUTP" != "any" ]
then
	OUTLABEL="$OUTP"
fi

if [ "$TARP" != "any" ]
then
	TARLABEL="$TARP"
fi

PATTERN="$OUTLABEL$MID$TARLABEL"

# Note that Node/Edge filtering is also exclusive.
if [[ $FLAGS == *N* ]]
then
	PATTERN="^\*N.*$PATTERN"
elif [[ $FLAGS == *E* ]]
then	
	PATTERN="^\*E.*$PATTERN"
fi

# Use extended regular expressions to ease usage.
# FLIST allows the complement to be returned if desired.
CFILES=`grep $FLIST -E "$PATTERN" $CFILES`

# Write the matching file names on standard output.
for file in $CFILES
do
	echo `basename $file`
done