From 7f5fb24aec470c56df46caac9d46f3cb4d5224b2 Mon Sep 17 00:00:00 2001
From: mrustl <michael.rustler@kompetenz-wasser.de>
Date: Fri, 28 Jun 2024 16:25:52 +0200
Subject: [PATCH] Fix :bug: in read_balance()

---
 NAMESPACE        |  1 +
 R/read_balance.R | 22 ++++++++++++++++------
 R/read_profile.R |  3 ++-
 3 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/NAMESPACE b/NAMESPACE
index a99451d..1c770cf 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -41,6 +41,7 @@ importFrom(readr,read_delim)
 importFrom(readr,read_fwf)
 importFrom(readr,read_table)
 importFrom(rlang,.data)
+importFrom(stats,median)
 importFrom(stats,setNames)
 importFrom(stringr,str_detect)
 importFrom(stringr,str_extract)
diff --git a/R/read_balance.R b/R/read_balance.R
index 446d84e..c1edc69 100644
--- a/R/read_balance.R
+++ b/R/read_balance.R
@@ -48,17 +48,27 @@ bal_id_start <- grep("Length", block_sel_txt)
 bal_id_end <- length(block_sel_txt)
 
 
-balance <- lapply(block_sel_txt[bal_id_start:bal_id_end], function(x) {
-  stringr::str_extract_all(x, "\\d+?\\.\\d+")[[1]] %>% as.double() %>% t() %>%
-    tibble::as_tibble()
-}) %>%
-  dplyr::bind_rows()
+# Funktion zur Extraktion der Fließkommazahlen
+extract_floats <- function(text) {
+  as.numeric(unlist(regmatches(text, gregexpr("-?\\d*\\.\\d+(?:E[+-]?\\d+)?", text))))
+}
+
+
+# Anwenden der Funktion auf den gesamten Text
+float_numbers_list <- lapply(block_sel_txt[bal_id_start:bal_id_end], extract_floats)
+
+# Erstellen eines DataFrames mit drei Spalten
+balance <- do.call(rbind, lapply(float_numbers_list, function(x) {
+  length(x) <- 3  # Setze die Länge auf 3, um sicherzustellen, dass alle Einträge drei Spalten haben
+  return(x)
+})) %>%
+  tibble::as_tibble()
 
 names(balance) <- sprintf("id_%d", subregion_ids)
 
 
 parvals <- block_sel_txt[bal_id_start:bal_id_end] %>%
-  stringr::str_remove_all("-?\\d+?\\.\\d+E\\+?-?\\d\\d") %>%
+  stringr::str_remove_all("-?\\d*\\.\\d+(?:E[+-]?\\d+)?") %>%
   stringr::str_trim()
 
 parvals_df <- parvals %>%
diff --git a/R/read_profile.R b/R/read_profile.R
index 76fa2c9..0ac626f 100644
--- a/R/read_profile.R
+++ b/R/read_profile.R
@@ -5,6 +5,7 @@
 #' @return tibble with PROFILE.out data
 #' @export
 #' @importFrom stringr str_replace
+#' @importFrom stats median
 read_profile <- function(path) {
 
   lines <- readLines(path)
@@ -26,7 +27,7 @@ read_profile <- function(path) {
                            stringr::str_split(" ", simplify = TRUE) %>%
                            as.vector() %>% tolower())
 
-  header_clean <- if(median(ncols) > length(header_names_file)) {
+  header_clean <- if(stats::median(ncols) > length(header_names_file)) {
     string_conc <- sprintf("conc%d", seq_len(median(ncols) - length(header_names_file))+1)
 
     c(stringr::str_replace(header_names_file, "conc", "conc1"),