context("de_serialize")

data_bin_file <<- "/tmp/epclust_test.bin"
unlink(data_bin_file)

test_that("serialization + getDataInFile retrieve original data / from matrix",
{
	#dataset 200 lignes / 30 columns
	data_ascii = matrix(runif(200*30,-10,10),ncol=30)
	nbytes = 4 #lead to a precision of 1e-7 / 1e-8
	endian = "little"

	#Simulate serialization in one single call
	serialize(data_ascii, data_bin_file, 500, ",", nbytes, endian)
	expect_equal(file.info(data_bin_file)$size, length(data_ascii)*nbytes+8)
	for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
	{
		data_lines = getDataInFile(indices, data_bin_file, nbytes, endian)
		expect_equal(data_lines, data_ascii[indices,], tolerance=1e-6)
	}
	unlink(data_bin_file)

	#...in several calls (last call complete, next call NULL)
	for (i in 1:20)
		serialize(data_ascii[((i-1)*10+1):(i*10),], data_bin_file, 20, ",", nbytes, endian)
	expect_equal(file.info(data_bin_file)$size, length(data_ascii)*nbytes+8)
	for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
	{
		data_lines = getDataInFile(indices, data_bin_file, nbytes, endian)
		expect_equal(data_lines, data_ascii[indices,], tolerance=1e-6)
	}
	unlink(data_bin_file)
})

test_that("serialization + getDataInFile retrieve original data / from connection",
{
	#dataset 300 lignes / 50 columns
	data_csv = system.file("testdata","de_serialize.csv",package="epclust")
	nbytes = 8
	endian = "big"
	data_ascii = as.matrix(read.csv(test_series, sep=";", header=FALSE)) #for ref

	#Simulate serialization in one single call
	serialize(data_csv, data_bin_file, 350, ";", nbytes, endian)
	expect_equal(file.info(data_bin_file)$size, 300*50*8+8)
	for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
	{
		#HACK: as.matrix(as.data.frame( )) required to match (ref) data structure
		data_lines = as.matrix(as.data.frame( getDataInFile(indices,data_bin_file,nbytes,endian) ))
		expect_equal(data_lines, data_ascii[indices,])
	}
	unlink(data_bin_file)

	#...in several calls / chunks of 29 --> 29*10 + 10, incomplete last
	data_con = file(data_csv, "r")
	serialize(data_con, data_bin_file, 29, ";", nbytes, endian)
	expect_equal(file.info(data_bin_file)$size, 300*50*8+8)
	for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
	{
		data_lines = as.matrix(as.data.frame( getDataInFile(indices,data_bin_file,nbytes,endian) ))
		expect_equal(data_lines, data_ascii[indices,])
	}
	unlink(data_bin_file)
	#close(data_con) --> done in serialize()
})