From f50a51035dae4978a3cca29949fd7755adcd06ec Mon Sep 17 00:00:00 2001
From: Tamas Stirling <stirling.tamas@gmail.com>
Date: Fri, 19 Jul 2024 21:45:51 +0200
Subject: [PATCH] Fix ncbi_recover_id() for duplicates

---
 NAMESPACE                             | 1 +
 R/ncbi_recover_id.R                   | 3 ++-
 tests/testthat/test-ncbi_recover_id.R | 7 +++++++
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/NAMESPACE b/NAMESPACE
index 2ea93ba..26bf222 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -23,6 +23,7 @@ export(parse_report)
 importFrom(curl,curl_download)
 importFrom(curl,handle_setopt)
 importFrom(curl,new_handle)
+importFrom(dplyr,"%>%")
 importFrom(dplyr,left_join)
 importFrom(httr,RETRY)
 importFrom(httr,content)
diff --git a/R/ncbi_recover_id.R b/R/ncbi_recover_id.R
index be7435f..ba0aa66 100644
--- a/R/ncbi_recover_id.R
+++ b/R/ncbi_recover_id.R
@@ -19,6 +19,7 @@
 #' uid <- ncbi_get_uid("GCF_000002435.2", db = "assembly")
 #' ncbi_recover_id(uid)
 #' }
+#' @importFrom dplyr %>%
 #' @export
 ncbi_recover_id <- function(
     query,
@@ -67,7 +68,7 @@ ncbi_recover_id <- function(
   out <- tibble::tibble(
     uid = as.numeric(unname(sapply(summaries, function(x) x$uid))),
     id = id
-  )
+  ) %>% dplyr::distinct()
   if ("ncbi_uid" %in% class(query)) {
     out <- dplyr::left_join(
       tibble::tibble(query = query$uid), 
diff --git a/tests/testthat/test-ncbi_recover_id.R b/tests/testthat/test-ncbi_recover_id.R
index 818898a..0033534 100644
--- a/tests/testthat/test-ncbi_recover_id.R
+++ b/tests/testthat/test-ncbi_recover_id.R
@@ -14,3 +14,10 @@ test_that("ncbi_recover_id() works with UIDs", {
   
   expect_equal(examples$assembly, ids)
 })
+
+test_that("ncbi_recover_id() works with duplicates", {
+  uids <- c(2597423, 2597423)
+  ids <- ncbi_recover_id(uids, db = "biosample")
+  
+  expect_equal(ids, c("SAMN02597423", "SAMN02597423"))
+})