# Copyleft Gary Feng, 2008

# this script takes TOBII *FXD.txt file as input, 
# and produce a data matrix with subject number as a separate column
# it also drops all other info in the header, but see the code for adding
# whatever info you want.
# 
# This script can process multiple files at the same time. See Usage

# Usage:
# first make sure you are in the same directory as the data file(s). 
#    1. open the DOS window by going to "Start->Run", and type "cmd", then "Enter".
#    2. to see the current directory, type in "DIR" and "enter" aka "return".
#    3. to change directory, type "CD c:\whatever\directory\you\need\to". 
#    4. type something like "gawk -f tobii_fxd_addsubjnum.awk mw6FXD.txt", 
#        and replace the last file name. You can also process all files with names 
#        with a particular pattern. For example, 
# "gawk -f tobii_fxd_addsubjnum.awk *.txt" will process all files in the current directory
#        that ends with the ".txt" extention. Be careful not to include files you don't want
#       Output will be displayed on the screen. Check to see if it looks right. 
#    5. When you feel like it's correct, do the following:
#        Press the upper-arrow key to bring back the last command you typed in; if this doesn
#            work you can either try F3, or type in again.
#        Add to the end " >outputfilename.txt" (change filename to whatever you need, or else 
#            the file will be overwritten if it already exists). The command now reads:
# "gawk -f tobii_fxd_addsubjnum.awk mw6FXD.txt >outputfilename.txt"
#        Press "Enter", and you should see a new file created. 
#        You can now open the new file in Excel or a text editor.



##################################################
# Script starts here
##################################################
# 

####################
# BEGIN is a keyword, and the commands after it is executed
#    before anything is read from the input TXT file
# We use it to set up some variables
#
BEGIN {

	# FS is for input Field Separator, and we define it as either space(s) or the tab key	
	FS="[ ]+|\t"
	
	# OFS is for Output Field Separator; we use Tab
	OFS="\t"
	
	study = ""
	subj=""
}

####################
# Now GAWK automatically reads in a line from the input file, compare to pattern(s) defined below
#   and if a pattern matches, the corresponding commands will be executed.
# Each line is compared to all patterns defined here. 
# 

####################
# first, we define the pattern for "study name"
# any line starting with "Study:" will match; the "^" sign is the regular expression for "beginning of a line"

/^Study:/ {
	# now what to do when this matches
	# we get the study name, which is the line substracting "Study: "
	# substr(STRING, Starting position, [optional length])
	study = substr($0,7)
}

####################
# Here we get the subject number;
# 
/^Subject:/ {
	# now this time I have to get the real 
	subj=substr($0,9)
}

####################
# now match the fixations, which are lines starting with a number
# in Regular Expression, [0-9] means any single digit between 0 and 9. 
# similarly, [a-zA-Z] means any lower or upper case single letter. 

/^[0-9]/ {
	# normally we want to make sure we have subject number and study name set before the output
	# but here we assume the FXD file is always well-formed and the header info is always before
	# the fixations. In this case we simply:
	
	# now we print the study name, subject number, and the Fixation line.
	print study, subj, $0
}

####################
# END is a keyword, and the commands after it is executed
#    after everything is read from the input TXT file.
# We don't do anything with it now.

END {
	# doing nothing special here
}