use glims_portal_read

DESCRIPTION

@@ -43,7 +43,6 @@ Imports:
     readr,
     RJSONIO,
     rlang,
-    rmarkdown,
     scales,
     sessioninfo,
     tibble,
@@ -52,6 +51,7 @@ Suggests:
     SparkR,
     DBI,
     RAthena,
+    rmarkdown,
     testthat (>= 3.0.0)
 Roxygen: list(markdown = TRUE,
               roclets = c("namespace", "rd", "roxytest::testthat_roclet"))

NAMESPACE

@@ -49,7 +49,8 @@ export(gds_file_presignedurl)
 export(gds_files_list)
 export(gds_files_list_filter_relevant)
 export(gds_volumes_list)
-export(glims_read)
+export(glims_excel_read)
+export(glims_portal_read)
 export(ica_token_validate)
 export(match_regex)
 export(meta_bcl_convert)

R/portal_meta.R

@@ -886,3 +886,45 @@ portal_meta_read_athena_tmp <- function(x = NULL) {
   RAthena::dbGetQuery(con, q1) |>
     tibble::as_tibble()
 }
+
+#' Read Portal Limsrow Table
+#'
+#' Reads rows from the data portal's limsrow table, given a set of `LibraryID`s
+#' to query.
+#'
+#' @param libids Character vector of LibraryID values to query for.
+#'
+#' @return Tibble with all rows from the data portal limsrow table where
+#' there are hits with the `library_id` column.
+#' @export
+glims_portal_read <- function(libids) {
+  assertthat::assert_that(!is.null(libids), all(grepl("^L", libids)))
+  libids <- unique(libids)
+  RAthena::RAthena_options(clear_s3_resource = FALSE)
+  con <- DBI::dbConnect(
+    RAthena::athena(),
+    work_group = "data_portal",
+    rstudio_conn_tab = FALSE
+  )
+  q_quote <- shQuote(paste(libids, collapse = "|"))
+  q1 <- glue(
+    'SELECT * FROM "data_portal"."data_portal"."data_portal_limsrow" where REGEXP_LIKE("library_id", {q_quote});'
+  )
+  d <- RAthena::dbGetQuery(con, q1) |>
+    tibble::as_tibble()
+  DBI::dbDisconnect(con)
+  d
+}
+
+#' Read Google LIMS
+#'
+#' Reads UMCCR's Google LIMS spreadsheet.
+#'
+#' @return Tibble with all columns and rows from the Google LIMS spreadsheet.
+#' @export
+glims_excel_read <- function() {
+  lims_key <- googledrive::drive_find("^Google LIMS$", shared_drive = "LIMS")$id
+  lims <- lims_key |>
+    googlesheets4::read_sheet("Sheet1", na = c(".", "", "-"), col_types = "c")
+  lims |> readr::type_convert(col_types = readr::cols(.default = "c", Timestamp = "T"))
+}

R/utils.R

@@ -165,18 +165,6 @@ read_jsongz_rjsonio <- function(x, ...) {
   RJSONIO::fromJSON(x, ...)
 }
 
-#' Read Google LIMS
-#'
-#' Reads UMCCR's Google LIMS spreadsheet.
-#'
-#' @return Tibble with all columns and rows from the Google LIMS spreadsheet.
-#' @export
-glims_read <- function() {
-  lims_key <- googledrive::drive_find("^Google LIMS$", shared_drive = "LIMS")$id
-  lims <- lims_key |>
-    googlesheets4::read_sheet("Sheet1", na = c(".", "", "-"), col_types = "c")
-  lims |> readr::type_convert(col_types = readr::cols(.default = "c", Timestamp = "T"))
-}
 
 
 #' @noRd

inst/rmd/umccr_portal/portal_summary.Rmd

@@ -126,8 +126,10 @@ add_totals <- function(x) {
 # Get metadata for workflows run within the date range
 # options(width = 150)
 fmt1 <- "%Y-%m-%dT%H:%M:%S"
-date_start <- as.POSIXct("2024-02-21T00:00:01", format = fmt1)
-date_end <- as.POSIXct("2024-02-23T23:59:59", format = fmt1)
+dstart <- "2024-03-08"
+dend <- "2024-03-10"
+date_start <- as.POSIXct(glue("{dstart}T00:00:01"), format = fmt1)
+date_end <- as.POSIXct(glue("{dend}T23:59:59"), format = fmt1)
 wf_order <- c(
   "bcl_convert",
   "tso_ctdna_tumor_only",
@@ -146,11 +148,11 @@ wf_order <- c(
 
 invisible(capture.output(dracarys:::awsvault_profile("upro")))
 lims_rds <- here(glue("nogit/data_portal/lims/{as.Date(date_end)}.rds"))
-# lims_raw <- dracarys::glims_read()
+# lims_raw <- dracarys::glims_read() # TODO: use glims_portal_read
 # saveRDS(lims_raw, file = lims_rds)
 lims_raw <- readr::read_rds(lims_rds)
 pmeta_rds <- here(glue("nogit/data_portal/workflows/{as.Date(date_end)}.rds"))
-wf_query <- 'WHERE "start" >= date(\'2024-02-21\') AND "start" <= date(\'2024-02-24\') ORDER BY "start" DESC;'
+wf_query <- glue('WHERE "start" >= date(\'{dstart}\') AND "start" <= date(\'{dend}\') ORDER BY "start" DESC;')
 
 # pmeta_raw <- dracarys:::portal_meta_read_athena_tmp(wf_query)
 # saveRDS(pmeta_raw, file = pmeta_rds)
@@ -241,7 +243,7 @@ blank_lines()
 
 ## RuntimeVis
 
-```{r vistime, fig.width=20, fig.height = 13}
+```{r vistime, fig.width=20, fig.height = 16}
 p1 <- pmeta_sumy |>
   dplyr::arrange(sbj_lib, type_name) |>
   dplyr::group_by(sbj_lib, type_name) |>

inst/rmd/umccr_workflows/alignment_qc/test.R

@@ -32,6 +32,7 @@ dp_workflow_read <- function(start_date) {
   d
 }
 
+# TODO: use dracarys::glims_portal_read
 dp_lims_read <- function(libids) {
   assertthat::assert_that(!is.null(libids), all(grepl("^L", libids)))
   libids <- unique(libids)
@@ -52,7 +53,7 @@ dp_lims_read <- function(libids) {
 }
 
 # first read in the workflows table, extract metadata, then join with lims
-start_date <- "2024-02-20"
+start_date <- "2024-03-08"
 p_raw <- dp_workflow_read(start_date)
 
 wgs <- p_raw |>