#!/bin/ksh
# USAGE: mvhyphen
# DESCRIPTION:
#	This script depends on having two variables defined:
#	SRCDIR:	Absolute pathname of directory containing files to be
#		processed.  Results are unspecified in there are any
#		subdirectories in this directory.
#	DESTDIR:Destination base directory.  This can be an absolute
#		pathname or a pathname relative to $SRCDIR.  (whichever
#		of these is shorter is preferred.)

#	This script moves to $SRCDIR and processes files with names
#	ending with ".txt".  Files with names containing a space are
#	ignored.  The 3rd line of each file is read.  If that line does
#	not match the pattern '^[[].*[]]', the file is also ignored.
#	Otherwise, the number of hyphens between the '[' and the first
#	comma or ']' after that are counted.  For each unique count
#	value, a list file is created in $DESTDIR named "listNH" where
#	"N" is the count value.  After the lists have been created,
#	files in each list will be moved from $SRCDIR to $DESTDIR/"N"H.
#	$DESTDIR and $DESTDIR/*H will be created if they are not already
#	present.

#	This script is OS X specific.  It is tuned to work within the
#	number of files awk can have open at once (stdin, stdout, and 17
#	more files) and uses the non-standard xargs -J option.  This
#	script whould be able to handle up to 33 different values for
#	the number of hyphens found in the 1st word in the 3rd line in
#	the files being processed.

# Initialize variables...
DESTDIR=../Syllable
SRCDIR=/Users/Nexeu/Documents/Dict

# Move to source directory and process the files found there...
cd "$SRCDIR" || exit 1
mkdir -p "$DESTDIR" || exit 2
find . -name '*.txt' ! -name '* *' |
awk -v sq="'" -v dest="$DESTDIR" '
{	# Open and read the 1st three lines of the file named on the input line.
	f = substr($0, 3)	# Discard the leading "./" from find.
	getline x < f
	getline x < f
	rc = getline x < f
	close(f)		# Close the file.
	if(rc != 1) {
		printf("Cannot read 3 lines from file: %s\n", f)
		next
	}
	if(x !~ /^[[].*[]]/) {
		printf("File line 3 bad format: %s\n", f)
		next
	}
	sub(/[],].*/, "", x)	# Discard all but 1st word...
	nh = gsub(/-/, "", x)	# count hyphens remaining on the line.
	if(!(nh in flist)) {
		# Add to the list of known counts.
		flist[nh] = sprintf("%s/list%dH", dest, nh)
		fd[nh] = ++nfd
	}
	if(fd[nh] <= 16) {
		# Write this filename directly to the appropriate list file.
		print sq f sq > flist[nh]
	} else {# Write the list file filename and this filename to stdout
		# to be processed by the 2nd awk in the pipeline...
		print sq flist[nh] sq f sq
	}
}' | \
# The following awk script interprets lines of the form:
#	'listfile_filename'file_to_be_move_filename'
# (without the double quotes) as a request to add the 2nd filename to
# the list of files in the 1st filename.  Other lines are copied
# directly to stdout assuming that they are diagnostics from the
# previous awk script.  If more than 17 different listfile pathnames are
# found in the input, lines for those listfiles will also be copied to
# stdout (so another copy of this script can be used to create upto 17
# more listfiles without running the find and the 1st awk again.
awk -F "'" -v sq="'" -v pat="^'[^']*'[^']*'$" '
$0 ~ pat { # Process listfile data lines...
	if(!($2 in flist) && nfd++ < 17) {
		# Add to known file list file array.
		flist[$2]
	}
	if($2 in flist) {
		print sq $3 sq > $2
		next
	}
	print "Too many list files to process..."
}
1'

# Now that all of the list files have been created, create the destination
# directories and move the files included in the list files into them.
for listpath in "$DESTDIR"/list*H
do	dirpath="${listpath%%list*}${listpath##*list}"
	printf 'Processing list file: "%s"\n' "$listpath"
	mkdir -p "$dirpath"
	xargs -J '#' mv '#' "$dirpath" < "$listpath" && rm "$listpath"
#	xargs -J '#' -t mv '#' "$dirpath" < "$listpath" && rm "$listpath"
done