Merge pull request #100 from capitalone/dev

Bug fix and update to CLA

.whitesource

@@ -0,0 +1,8 @@
+{
+  "checkRunSettings": {
+    "vulnerableCheckRunConclusionLevel": "failure"
+  },
+  "issueSettings": {
+    "minSeverityLevel": "LOW"
+  }
+}

CODEOWNERS

@@ -0,0 +1,3 @@
+
+# Currently sharing all of the files together
+* @sajohnston @KrishanBhasin

README.md

@@ -113,12 +113,6 @@ https://cran.r-project.org/package=dataCompareR
 
 ## External Contributors
 
-Contributors: We welcome your interest in Capital One’s Open Source Projects (the “Project”). 
+We welcome and appreciate your contributions! Before we can accept any contributions, we ask that you please be sure to sign the [Contributor License Agreement (CLA)](https://cla-assistant.io/capitalone/dataCompareR).
 
-Any Contributor to the project must accept and sign a CLA indicating agreement to the license terms. Except for the license granted in this CLA to Capital One and to recipients of software distributed by Capital One, you reserve all right, title, and interest in and to your contributions; this CLA does not impact your rights to use your own contributions for any other purpose. 
-
-[Link to Individual CLA](https://docs.google.com/forms/d/19LpBBjykHPox18vrZvBbZUcK6gQTj7qv1O5hCduAZFU/viewform)
-
-[Link to Corporate CLA ](https://docs.google.com/forms/d/e/1FAIpQLSeAbobIPLCVZD_ccgtMWBDAcN68oqbAJBQyDTSAQ1AkYuCp_g/viewform)
-
-This project adheres to the [Open Source Code of Conduct](https://developer.capitalone.com/single/code-of-conduct/). By participating, you are expected to honor this code. 
+This project adheres to the [Open Source Code of Conduct](https://developer.capitalone.com/resources/code-of-conduct/). By participating, you are expected to honor this code. 

dataCompareR/R/pd_matchRows.R

@@ -140,8 +140,8 @@ matchSingleIndex <- function(df_a, df_b, index_key, original_keys)
 #'        contains the vectors for the dropped rows
 matchMultiIndex <- function(df_a, df_b, indices)
 {
-  df_a$dataCompareR_merged_indices <- do.call(paste,c(df_a[indices],sep = ""))
-  df_b$dataCompareR_merged_indices <- do.call(paste,c(df_b[indices],sep = ""))
+  df_a$dataCompareR_merged_indices <- do.call(paste,c(df_a[indices],sep = "_"))
+  df_b$dataCompareR_merged_indices <- do.call(paste,c(df_b[indices],sep = "_"))
 
   mtchedData <- matchSingleIndex(df_a, df_b, 'dataCompareR_merged_indices', indices)
 

dataCompareR/tests/testthat/testMatchMultiIndex.R

@@ -93,3 +93,37 @@ test_that("matchMultiIndex doesn't produce any warnings when creating output" ,
   expect_message(summary(a),"dataCompareR is generating the summary...")
 
 })
+
+test_that("Merged indices remain unique in multi-index cases", {
+
+  # Create data frames with values that if merged without a separator, would
+  # produce the same merged index. 
+
+  # No differences
+  ky <- c(1, 2)
+  ky1 <- c("a1", "a")
+  ky2 <- c("b", "1b")
+  df1 <- data.frame(ky1, ky2, ky, stringsAsFactors = FALSE)
+
+  # Second data frame. Same as first
+  df2 <- df1
+
+  # Matching data fame will be the same as well
+  dfMtch <- df1
+
+  # Do the actual matching. If the indices weren't unique, an error would be raised
+  # This shouldn't produce any errors because they are separate indices
+  expect_silent(mtch <- matchMultiIndex(df1, df2, c("ky1", "ky2"))) # Expected matched subset
+
+  # Check that the output is still as expected
+  mtchSorted <- arrange(mtch[[1]], ky1, ky2)
+  dfMtchSorted <- arrange(dfMtch, ky1, ky2)
+
+  expect_equal(mtchSorted[,1], dfMtchSorted[,1])
+  expect_equal(mtchSorted[,2], dfMtchSorted[,2]) 
+
+  mtch2Sorted <- arrange(mtch[[2]], ky1, ky2)
+
+  expect_equal(mtch2Sorted[,1], dfMtchSorted[,1]) 
+  expect_equal(mtch2Sorted[,2], dfMtchSorted[,2]) 
+})

dataCompareR/tests/testthat/testMatchRows.R

@@ -166,3 +166,37 @@ test_that("matchRows correctly finds matching rows", {
   expect_equal(mtchSorted32[[1]], msgB1) # Missing indices from A
   expect_equal(mtchSorted32[[2]], msgB2) # Missing indices from A  
 })
+
+test_that("Merged indices remain unique in multi-index cases", {
+
+  # Create data frames with values that if merged without a separator, would
+  # produce the same merged index. 
+
+  # No differences
+  ky <- c(1, 2)
+  ky1 <- c("a1", "a")
+  ky2 <- c("b", "1b")
+  df1 <- data.frame(ky1, ky2, ky, stringsAsFactors = FALSE)
+
+  # Second data frame. Same as first
+  df2 <- df1
+
+  # Matching data fame will be the same as well
+  dfMtch <- df1
+
+  # Do the actual matching. If the indices weren't unique, an error would be raised
+  # This shouldn't produce any errors because they are separate indices
+  expect_silent(mtch <- matchRows(df1, df2, c("ky1", "ky2"))) # Expected matched subset
+
+  # Check that the output is still as expected
+  mtchSorted <- arrange(mtch[[1]], ky1, ky2)
+  dfMtchSorted <- arrange(dfMtch, ky1, ky2)
+
+  expect_equal(mtchSorted[,1], dfMtchSorted[,1])
+  expect_equal(mtchSorted[,2], dfMtchSorted[,2]) 
+
+  mtch2Sorted <- arrange(mtch[[2]], ky1, ky2)
+
+  expect_equal(mtch2Sorted[,1], dfMtchSorted[,1]) 
+  expect_equal(mtch2Sorted[,2], dfMtchSorted[,2]) 
+})