From e1daecda64e1b89702c2dd3acb25aa03afff1e89 Mon Sep 17 00:00:00 2001
From: Michael Tran <mtran256@uwo.ca>
Date: Tue, 21 Oct 2025 10:08:50 -0400
Subject: [PATCH 1/3] fix: properly skip tsv comments instead of hardcoding
 skips

---
 R/utils-httr2.R                           | 7 ++++++-
 tests/testthat/test_cellosaurus_helpers.R | 8 ++++----
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/R/utils-httr2.R b/R/utils-httr2.R
index 171e0d7..cbcbce3 100644
--- a/R/utils-httr2.R
+++ b/R/utils-httr2.R
@@ -61,5 +61,10 @@
 #' @noRd
 #' @keywords internal
 .parse_resp_tsv <- function(resp, show_col_types = FALSE, skip = 0) {
-  readr::read_tsv(resp$body, skip = skip, show_col_types = show_col_types)
+  readr::read_tsv(
+    resp$body,
+    skip = skip,
+    show_col_types = show_col_types,
+    comment = "#"
+  )
 }
diff --git a/tests/testthat/test_cellosaurus_helpers.R b/tests/testthat/test_cellosaurus_helpers.R
index 10aa3eb..87937c6 100644
--- a/tests/testthat/test_cellosaurus_helpers.R
+++ b/tests/testthat/test_cellosaurus_helpers.R
@@ -39,9 +39,9 @@ test_that(".build_cellosaurus_request is acting as expected", {
   expect_equal(request$url, expected)
 
   response <- AnnotationGx:::.perform_request(request) |>
-    AnnotationGx:::.parse_resp_tsv(show_col_types = FALSE, skip = 14)
+    AnnotationGx:::.parse_resp_tsv(show_col_types = FALSE)
   expect_class(response, "spec_tbl_df")
-  expect_gte(nrow(response), 1)
+  expect_equal(nrow(response), 1)
 
   request2 <- AnnotationGx:::.build_cellosaurus_request(
     query = "id:HeLa",
@@ -74,8 +74,8 @@ test_that(".build_cellosaurus_request is acting as expected", {
     "https://api.cellosaurus.org/search/cell-line?q=id%3AHeLa&sort=ac%20asc&fields=id%2Cac%2Csy%2Cacas%2Csx%2Cag%2Cdi%2Cdio%2Cdin%2Cdr%2Ccell-type%2Cderived-from-site%2Cmisspelling%2Cdt%2Cdtc%2Cdtu%2Cdtv%2Cgenome-ancestry&format=tsv&rows=2"
   )
   response <- AnnotationGx:::.perform_request(request2) |>
-    AnnotationGx:::.parse_resp_tsv(show_col_types = FALSE, skip = 14)
-  expect_gte(nrow(response), 1)
+    AnnotationGx:::.parse_resp_tsv(show_col_types = FALSE)
+  expect_equal(nrow(response), 2)
 })
 
 test_that(".build_cellosaurus_request accepts documented sort fields", {

From 10fe41496ed3c566e350a9269814531dc9878d41 Mon Sep 17 00:00:00 2001
From: Michael Tran <mtran256@uwo.ca>
Date: Tue, 21 Oct 2025 11:51:09 -0400
Subject: [PATCH 2/3] refactor: streamline cellosaurus column ordering

---
 R/cellosaurus.R | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/R/cellosaurus.R b/R/cellosaurus.R
index 05dbb97..53b550e 100644
--- a/R/cellosaurus.R
+++ b/R/cellosaurus.R
@@ -206,16 +206,13 @@ mapCell2Accession <- function(
   core_cols <- c("cellLineName", "accession")
   existing_core <- core_cols[core_cols %in% names(responses_dt)]
   if (length(existing_core) > 0L) {
-    query_cols <- if (include_query) {
-      grep("^query", names(responses_dt), value = TRUE)
-    } else {
-      character(0)
+    other_cols <- setdiff(names(responses_dt), existing_core)
+    if (include_query) {
+      query_cols <- grep("^query", other_cols, value = TRUE)
+      non_query_cols <- setdiff(other_cols, query_cols)
+      other_cols <- c(non_query_cols, query_cols)
     }
-    extra_cols <- setdiff(names(responses_dt), c(existing_core, query_cols))
-    data.table::setcolorder(
-      responses_dt,
-      c(existing_core, extra_cols, query_cols)
-    )
+    data.table::setcolorder(responses_dt, c(existing_core, other_cols))
   }
 
   return(responses_dt)

From 6b1e9af074f6da9ed9a968ec3b89599451524152 Mon Sep 17 00:00:00 2001
From: Michael Tran <mtran256@uwo.ca>
Date: Tue, 21 Oct 2025 17:09:46 -0400
Subject: [PATCH 3/3] chore: restore cellosaurus column ordering

---
 R/cellosaurus.R | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/R/cellosaurus.R b/R/cellosaurus.R
index 53b550e..05dbb97 100644
--- a/R/cellosaurus.R
+++ b/R/cellosaurus.R
@@ -206,13 +206,16 @@ mapCell2Accession <- function(
   core_cols <- c("cellLineName", "accession")
   existing_core <- core_cols[core_cols %in% names(responses_dt)]
   if (length(existing_core) > 0L) {
-    other_cols <- setdiff(names(responses_dt), existing_core)
-    if (include_query) {
-      query_cols <- grep("^query", other_cols, value = TRUE)
-      non_query_cols <- setdiff(other_cols, query_cols)
-      other_cols <- c(non_query_cols, query_cols)
+    query_cols <- if (include_query) {
+      grep("^query", names(responses_dt), value = TRUE)
+    } else {
+      character(0)
     }
-    data.table::setcolorder(responses_dt, c(existing_core, other_cols))
+    extra_cols <- setdiff(names(responses_dt), c(existing_core, query_cols))
+    data.table::setcolorder(
+      responses_dt,
+      c(existing_core, extra_cols, query_cols)
+    )
   }
 
   return(responses_dt)