From c94bb00bbf9c40258c018d965bafaf28633fa259 Mon Sep 17 00:00:00 2001
From: orichters <oliverr@pik-potsdam.de>
Date: Tue, 8 Oct 2024 16:38:55 +0200
Subject: [PATCH] undo everything, add check.duplicates = FALSE to
 read.snapshot

---
 DESCRIPTION       |  1 -
 NAMESPACE         |  1 -
 R/read.snapshot.R | 23 ++++++++---------------
 3 files changed, 8 insertions(+), 17 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index a113b30..a16d192 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -24,7 +24,6 @@ Depends:
 Imports:
     cli,
     countrycode,
-    data.table,
     dplyr (>= 1.1.1),
     forcats (>= 1.0.0),
     ggplot2,
diff --git a/NAMESPACE b/NAMESPACE
index 5bb2dd0..77869d6 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -94,7 +94,6 @@ import(dplyr)
 import(utils)
 importFrom(cli,cli_abort)
 importFrom(countrycode,countrycode)
-importFrom(data.table,fread)
 importFrom(dplyr,"%>%")
 importFrom(dplyr,across)
 importFrom(dplyr,anti_join)
diff --git a/R/read.snapshot.R b/R/read.snapshot.R
index 61aba31..3aa0bf5 100644
--- a/R/read.snapshot.R
+++ b/R/read.snapshot.R
@@ -20,11 +20,8 @@
 #' read.filter.snapshot("snapshot.csv", list(scenario = c("CurPol", "NDC"), region = "World"))
 #' }
 #'
-#' @importFrom data.table fread
 #' @importFrom dplyr filter
 #' @importFrom stats setNames
-#' @importFrom tidyr pivot_longer
-#' @importFrom readxl read_excel excel_sheets
 #'
 #' @export
 
@@ -79,17 +76,13 @@ read.snapshot <- function(file, keep = list(), filter.function = identity) {
     data <- filter.function(data)
     return(data)
   }
-  if (grepl("\\.rds$", tmpfile)) {
-    data <- as.quitte(readRDS(tmpfile), na.rm = TRUE)
-  } else if (grepl("\\.xlsx?$", tmpfile)) {
-    data <- read_excel(path = tmpfile, sheet = if ("data" %in% excel_sheets(tmpfile)) "data" else 1, guess_max = 21474836) %>%
-      pivot_longer(matches("[0-9]+"), names_to = "period", values_drop_na = TRUE)
-  } else {
-    sep <- if (grepl(",", read_lines(file = tmpfile, n_max = 1), fixed = TRUE)) "," else ";"
-    data <- fread(tmpfile, sep = sep, header = TRUE, na.strings =  c("UNDF", "NA", "N/A", "n_a", "")) %>%
-      as_tibble() %>%
-      pivot_longer(matches("[0-9]+"), names_to = "period", values_drop_na = TRUE)
-  }
+  # read file and do correct filtering
+  data <- read.quitte(tmpfile,
+                      na.strings = c("UNDF", "NA", "N/A", "n_a", ""),
+                      quote = '"',
+                      drop.na = TRUE,
+                      check.duplicates = FALSE,
+                      filter.function = joinedfilter)
   unlink(tmpfile)
-  return(joinedfilter(as.quitte(data)))
+  return(data)
 }