R Under development (unstable) (2023-07-19 r84711 ucrt) -- "Unsuffered Consequences"
Copyright (C) 2023 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> 
> source("helpers.R")
> 
> expect_equal_pairs <- function(x, y) {
+   setkey(x, .x, .y)
+   setkey(y, .x, .y)
+   expect_equal(names(x), names(y))
+   for (col in names(x))
+     expect_equal(x[[col]], y[[col]], attributes = FALSE)
+ }
> 
> library(reclin2)
Loading required package: data.table

Attaching package: 'reclin2'

The following object is masked from 'package:base':

    identical

> library(parallel)
> 
> # Prepare data
> data(linkexample1)
> data(linkexample2)
> linkexample1$postcode[1] <- NA
> linkexample1$postcode[3] <- "6789 XY"
> 
> # What the result should look like
> pairs_ref <- data.table(
+   .x = c(1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L), 
+   .y = c(1L, 1L, 2L, 3L, 3L, 4L, 5L, 1L, 2L, 3L, 1L, 2L, 3L, 4L, 5L), 
+   firstname = c(FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, TRUE, 
+       FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, TRUE, FALSE),
+   lastname = c(TRUE, TRUE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, 
+     FALSE, TRUE, FALSE, FALSE, TRUE, TRUE, TRUE)
+ )
> 
> # Regular pairs
> pairs1 <- pair_blocking(linkexample1, linkexample2, on = "postcode")
> pairs2 <- pair_blocking(linkexample1, linkexample2, on = "lastname")
> pairs <- merge_pairs(pairs1, pairs2)
> compare_pairs(pairs, on = c("firstname", "lastname"), inplace = TRUE)
> expect_equal_pairs(pairs, pairs_ref)
> 
> compare_pairs(pairs1, on = c("firstname", "lastname"), inplace = TRUE)
> compare_pairs(pairs2, on = c("address", "lastname"), inplace = TRUE)
> pairs <- merge_pairs(pairs1, pairs2)
> expect_equal(sort(names(pairs)), c(".x", ".y", "address", "firstname", "lastname"))
> expect_equal(is.na(pairs$address), !is.na(pairs$firstname))
> 
> 
> 
> # Cluster pairs
> library(parallel)
> cl <- makeCluster(2)
> pairs1c <- cluster_pair_blocking(cl, linkexample1, linkexample2, on = "postcode", name="a")
> pairs2c <- cluster_pair_blocking(cl, linkexample1, linkexample2, on = "lastname", name="b")
> pairsc <- merge_pairs(pairs1c, pairs2c)
> compare_pairs(pairsc, on = c("firstname", "lastname"), inplace = TRUE)
> pairsc_local <- cluster_collect(pairsc)
> expect_equal_pairs(pairsc_local, pairs_ref)
> 
> compare_pairs(pairs1c, on = c("firstname", "lastname"))
> compare_pairs(pairs2c, on = c("address", "lastname"))
> pairsc <- merge_pairs(pairs1c, pairs2c)
> pairsc_local <- cluster_collect(pairsc)
> expect_equal(sort(names(pairsc_local)), c(".x", ".y", "address", "firstname", "lastname"))
> expect_equal(is.na(pairsc_local$address), !is.na(pairsc_local$firstname))
> 
> stopCluster(cl)
> 
> pairs1 <- pair_blocking(linkexample1, linkexample2, on = "postcode")
> pairs2 <- pair_blocking(linkexample1, linkexample2, on = "lastname")
> pairs2 <- pairs2[FALSE, ]
> pairs <- merge_pairs(pairs1, pairs2)
> compare_pairs(pairs, on = c("firstname", "lastname"), inplace = TRUE)
> compare_pairs(pairs1, on = c("firstname", "lastname"), inplace = TRUE)
> expect_equal_pairs(pairs1, pairs)
> 
> 
> 
> proc.time()
   user  system elapsed 
   0.42    0.04    0.82