#!/bin/bash
# wut-dl-sort-txmode
#
# XXX  This script removes directories in data/  !!! XXX
#
# Populates the data/ directory from the download/dir.
# Does it just for a specific transmitter mode (encoding)
#
# Available encodings:
# 4FSK AFSK_TUBiX10 AFSK AHRPT AM APT ASK BPSK_PMT-A3 BPSK CERTO CW DBPSK DOKA
# DPSK DQPSK DSTAR DUV DVB-S2 FFSK FMN FM FSK_AX.25_G3RUH FSK_AX.100_Mode_5
# FSK_AX.100_Mode_6 FSK GFSK_Rktr GFSK GFSK/BPSK GMSK_USP GMSK HRPT LRPT LSB
# LoRa MFSK MSK_AX.100_Mode_5 MSK_AX.100_Mode_6 MSK OFDM OQPSK PSK31 PSK63 PSK
# QPSK31 QPSK63 QPSK SSTV USB WSJT 
#
# Encoding list generator:
# for i in `curl --silent https://db.satnogs.org/api/modes/ | jq  '.[] | .name' | sort -V | sed -e 's/"//g' -e 's/ /_/g' -e 's/\//_/g'` ; do echo -n "$i " ; done ; echo
#
# Usage:
# wut-dl-sort-txmode [Encoding] [Minimum Observation ID] [Maximum Observation ID]
# Example:
# wut-dl-sort-txmode CW 1467000 1470000
# For December, 2019 Example:
# wut-dl-sort-txmode CW 1292461 1470525
# For July, 2022 Example:
# wut-dl-sort-txmode BPSK1k2 6154228 6283338
#
# * 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="$1"
OBSIDMIN="$2"
OBSIDMAX="$3"
OBSID=$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 $OBSID.json | jq --compact-output '.[0] | {transmitter_mode}' | cut -f 2 -d ":" | sed -e 's/}//g' -e 's/"//g'`
	if [ "$OBSENC" = "$ENC" ] ; 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