#!/bin/bash
# wut-dl-sort-txmode-all
#
# Training of all waterfalls. Used for modes that have few samples.
#
# Populates the data/ directory from the download/dir.
# Does it just for a specific transmitter mode (encoding)
# Available encodings:
# AFSK AFSK1k2 AHRPT APT BPSK BPSK1k2 BPSK9k6 BPSK12k5 BPSK400 CERTO CW DUV
# FFSK1k2 FM FSK1k2 FSK4k8 FSK9k6 FSK19k2 GFSK1k2 GFSK2k4 GFSK4k8 GFSK9k6
# GFSK19k2 GFSK Rktr GMSK GMSK1k2 GMSK2k4 GMSK4k8 GMSK9k6 GMSK19k2 HRPT LRPT
# MSK1k2 MSK2k4 MSK4k8 PSK PSK31 SSTV USB WSJT
#
# XXX  This script removes directories in data/  !!! XXX
#
# Usage:
# wut-dl-sort-txmode-all [Minimum Observation ID] [Maximum Observation ID]
# Example:
# wut-dl-sort-txmode-all 1467000 1470000
# For December, 2019 Example:
# wut-dl-sort-txmode-all 1292461 1470525
# wut-dl-sort-txmode-all 1292434 1470525
#
# * Takes the files in the download/ dir.
# * Looks at the JSON files to see if it is :good", "bad", or "failed".
# * Hard link it in the appropriate data/ directory.
# * File is randomly copied to either data/train or data/val directory.
#
# Possible vetted_status: bad, failed, good, null, unknown.


OBSENC="ALL"
OBSIDMIN="$1"
OBSIDMAX="$2"
OBSID=$OBSIDMIN
DATADIR="/srv/satnogs/data/txmodes/$OBSENC"
DOWNDIR="/srv/satnogs/download"

mkdir -p $DATADIR
cd $DATADIR || exit

# Enable the following if you want to download waterfalls in this range:
#echo "Downloading Waterfalls"
#./wut-water-range $OBSIDMIN $OBSIDMAX

# XXX remove data/train and data/val directories XXX
echo "Removing subdirectories"
rm -rf train/ val/
# Create new empty dirs
mkdir -p train/good/ train/bad/ train/failed/
mkdir -p val/good/   val/bad/   val/failed/

# Then parse each file and link appropriately
echo "Parsing download/ directory for observation IDs $OBSIDMIN to $OBSIDMAX"
cd $DOWNDIR || exit

while [ $OBSID -lt $OBSIDMAX ]
        do cd $OBSID
	VET=`cat $OBSID.json | jq --compact-output '.[0] | {vetted_status}' | cut -f 2 -d ":" | sed -e 's/}//g' -e 's/"//g'`
	ENC=`cat $OBSID.json | jq --compact-output '.[0] | {transmitter_mode}' | cut -f 2 -d ":" | sed -e 's/}//g' -e 's/"//g'`
# Do all of them
	if [ "$OBSENC" = "$OBSENC" ] ; then
		RAND_DIR=`echo $((0 + RANDOM % 2))`
		if [ $RAND_DIR = 1 ] ; then
			CLASS_DIR="train"
		else
			CLASS_DIR="val"
		fi
		case "$VET" in
			bad) ln waterfall_$OBSID_*.png $DATADIR/$CLASS_DIR/$VET/
			;;
			good) ln waterfall_$OBSID_*.png $DATADIR/$CLASS_DIR/$VET/
			;;
			failed) ln waterfall_$OBSID_*.png $DATADIR/$CLASS_DIR/$VET/
			;;
			null) echo "null, not copying"
			;;
			unknown) echo "unknown, not copying"
			;;
		esac
	fi
        let OBSID=$OBSID+1
	cd ..
done