#include <stdlib.h>
#include <math.h>
#include <stdbool.h>

#ifndef M_PI
#define M_PI 3.14159265358979323846
#endif

// n: number of synchrones, m: length of a synchrone
float computeWerDist(float* s1, float* s2, int n, int m)
{
	//TODO: automatic tune of all these parameters ? (for other users)
	int nvoice = 4;
	//noctave 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
	int noctave = 13
	// 4 here represent 2^5 = 32 half-hours ~ 1 day
	//NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
	//R: scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1)
	int* scalevector = (int*)malloc( (noctave*nvoice-4 + 1) * sizeof(int))
	for (int i=4; i<=noctave*nvoice; i++)
		scalevector[i-4] = pow(2., (float)i/nvoice + 1.);
	//condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
	int s0 = 2;
	double w0 = 2*M_PI;
	bool scaled = false;
	int s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
	int totnoct = noctave + as.integer(s0log/nvoice) + 1





///TODO: continue



	computeCWT = function(i)
	{
		if (verbose)
			cat(paste("+++ Compute Rwave::cwt() on serie ",i,"\n", sep=""))
		ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
		totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
		ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
		#Normalization
		sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
		sqres <- sweep(ts.cwt,2,sqs,'*')
		sqres / max(Mod(sqres))
	}

	if (parll)
	{
		cl = parallel::makeCluster(ncores_clust)
		parallel::clusterExport(cl,
			varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
			envir=environment())
	}

	# (normalized) observations node with CWT
	Xcwt4 <-
		if (parll)
			parallel::parLapply(cl, seq_len(n), computeCWT)
		else
			lapply(seq_len(n), computeCWT)

	if (parll)
		parallel::stopCluster(cl)

	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
	fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
	if (verbose)
		cat("*** Compute WER distances from CWT\n")

	#TODO: computeDistances(i,j), et répartir les n(n-1)/2 couples d'indices
	#là c'est trop déséquilibré

	computeDistancesLineI = function(i)
	{
		if (verbose)
			cat(paste("   Line ",i,"\n", sep=""))
		for (j in (i+1):n)
		{
			#TODO: 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
			num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
			WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
			WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
			wer2    <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
			if (parll)
				synchronicity::lock(m)
			Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
			Xwer_dist[j,i] <- Xwer_dist[i,j]
			if (parll)
				synchronicity::unlock(m)
		}
		Xwer_dist[i,i] = 0.
	}

	parll = (requireNamespace("synchronicity",quietly=TRUE)
		&& parll && Sys.info()['sysname'] != "Windows")
	if (parll)
		m <- synchronicity::boost.mutex()

	ignored <-
		if (parll)
		{
			parallel::mclapply(seq_len(n-1), computeDistancesLineI,
				mc.cores=ncores_clust, mc.allow.recursive=FALSE)
		}
		else
			lapply(seq_len(n-1), computeDistancesLineI)
	Xwer_dist[n,n] = 0.

	mat_dists = matrix(nrow=n, ncol=n)
	#TODO: avoid this loop?
	for (i in 1:n)
		mat_dists[i,] = Xwer_dist[i,]
	mat_dists