epclust/tests/testthat/test.de_serialize.R

   1 context("de_serialize")
   2
   3 data_bin_file <<- "/tmp/epclust_test.bin"
   4 unlink(data_bin_file)
   5
   6 test_that("serialization + getDataInFile retrieve original data / from matrix",
   7 {
   8     #dataset 200 lignes / 30 columns
   9     data_ascii = matrix(runif(200*30,-10,10),ncol=30)
  10     nbytes = 4 #lead to a precision of 1e-7 / 1e-8
  11     endian = "little"
  12
  13     #Simulate serialization in one single call
  14     serialize(data_ascii, data_bin_file, 500, ",", nbytes, endian)
  15     expect_equal(file.info(data_bin_file)$size, length(data_ascii)*nbytes+8)
  16     for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
  17     {
  18         data_lines = getDataInFile(indices, data_bin_file, nbytes, endian)
  19         expect_equal(data_lines, data_ascii[indices,], tolerance=1e-6)
  20     }
  21     unlink(data_bin_file)
  22
  23     #...in several calls (last call complete, next call NULL)
  24     for (i in 1:20)
  25         serialize(data_ascii[((i-1)*10+1):(i*10),], data_bin_file, 20, ",", nbytes, endian)
  26     expect_equal(file.info(data_bin_file)$size, length(data_ascii)*nbytes+8)
  27     for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
  28     {
  29         data_lines = getDataInFile(indices, data_bin_file, nbytes, endian)
  30         expect_equal(data_lines, data_ascii[indices,], tolerance=1e-6)
  31     }
  32     unlink(data_bin_file)
  33 })
  34
  35 test_that("serialization + getDataInFile retrieve original data / from connection",
  36 {
  37     #dataset 300 lignes / 50 columns
  38     data_csv = system.file("testdata","de_serialize.csv",package="epclust")
  39     nbytes = 8
  40     endian = "big"
  41     data_ascii = as.matrix(read.csv(test_series, sep=";", header=FALSE)) #for ref
  42
  43     #Simulate serialization in one single call
  44     serialize(data_csv, data_bin_file, 350, ";", nbytes, endian)
  45     expect_equal(file.info(data_bin_file)$size, 300*50*8+8)
  46     for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
  47     {
  48         #HACK: as.matrix(as.data.frame( )) required to match (ref) data structure
  49         data_lines = as.matrix(as.data.frame( getDataInFile(indices,data_bin_file,nbytes,endian) ))
  50         expect_equal(data_lines, data_ascii[indices,])
  51     }
  52     unlink(data_bin_file)
  53
  54     #...in several calls / chunks of 29 --> 29*10 + 10, incomplete last
  55     data_con = file(data_csv, "r")
  56     serialize(data_con, data_bin_file, 29, ";", nbytes, endian)
  57     expect_equal(file.info(data_bin_file)$size, 300*50*8+8)
  58     for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
  59     {
  60         data_lines = as.matrix(as.data.frame( getDataInFile(indices,data_bin_file,nbytes,endian) ))
  61         expect_equal(data_lines, data_ascii[indices,])
  62     }
  63     unlink(data_bin_file)
  64     #close(data_con) --> done in serialize()
  65 })