Merge pull request #118 from hugomflavio/issue_103

Issue 103 update
hugomflavio · Oct 9, 2024 · 92d0904 · 92d0904
2 parents d7f157c + e56e9ba
commit 92d0904
Show file tree

Hide file tree

Showing 3 changed files with 55 additions and 39 deletions.
diff --git a/R/helper.R b/R/helper.R
@@ -688,21 +688,19 @@ splitSignals <- function(x) {
 }
 
 
-#' Convert Lotek CMDA log to csv
+#' Convert Lotek CDMA log to csv
 #' 
-#' Lotek CMDA logs are exported in TXT, and contain several chunks of
-#' of information. Importantly, the detections are saved in the timezone
-#' of the respective computer, as opposed to the more common UTC standard.
-#' Additionally, the date format also depends on the locale of the computer,
-#' and may therefore be incomprehensible for R without further assistance.
+#' Lotek CDMA logs are exported in TXT, and contain several chunks of
+#' of information. Importantly, the detections may be saved with a GMT offset,
+#' as opposed to the more common UTC standard.
+#' Additionally, the date format isn't the standard yyyy-mm-dd.
 #' 
-#' This function extracts the detections from the CMDA file, converts the
+#' This function extracts the detections from the CDMA file, converts the
 #' dates to yyyy-mm-dd, binds the time to the date and resets it to UTC, and
 #' ultimately converts the dataframe into the standard format accepted by actel.
 #'
 #' @param file the file name.
 #' @param date_format the format used by the computer that generated the file
-#' @param tz the timezone of the computer that generated the file.
 #'
 #' @examples
 #' # create a dummy detections file to read
@@ -718,6 +716,9 @@ splitSignals <- function(x) {
 #' Serial Number:      WHS3K-1234567
 #' Node ID:            10000
 #' 
+#' Receiver Settings:
+#' GMT Correction:     00:00
+#' 
 #' Decoded Tag Data:
 #' Date      Time             TOA       Tag ID    Type     Value     Power
 #' =======================================================================
@@ -738,16 +739,15 @@ splitSignals <- function(x) {
 #' sink()
 #' 
 #' # now read it
-#' x <- convertLotekCDMAFile(dummy_file, date_format = "%m/%d/%y", 
-#'                           tz = "Europe/Copenhagen")
+#' x <- convertLotekCDMAFile(dummy_file)
 #' 
 #' # the dummy file will be deleted automatically once you close this R session.
 #' 
 #' @return A data frame of standardized detections from the input file.
 #'
 #' @export
 #'
-convertLotekCDMAFile <- function(file, date_format, tz) {
+convertLotekCDMAFile <- function(file, date_format = "%m/%d/%y") {
   file_raw <- readLines(file)
 
   serial_n <- file_raw[grep("^Serial Number:", file_raw)]
@@ -759,17 +759,23 @@ convertLotekCDMAFile <- function(file, date_format, tz) {
     code_type <- NA
   }
 
+  gmt_cor <- file_raw[grep("^GMT Correction:", file_raw)]
+  gmt_cor <- sub("GMT Correction:\\s*", "", gmt_cor)
+  gmt_cor <- decimalTime(gmt_cor)
+
   det_start <- grep("=========", file_raw)[1]
   det_end <- grep("Receiver Sensor Messages:", file_raw)[1] - 2
 
   det_names <- file_raw[det_start-1]
   det_names <- sub("Tag ID", "Signal", det_names)
-  
-  output <- data.table::fread(file, fill = TRUE, 
+
+  output <- readr::read_fwf(file, 
     skip = det_start,
-    nrows = det_end - det_start,
-    showProgress = FALSE,
-    header = FALSE)
+    n_max = det_end - det_start,
+    show_col_types = FALSE)
+
+  output <- as.data.table(output)
+
   colnames(output) <- unlist(strsplit(det_names, "\\s\\s*"))
   output$CodeSpace <- code_type
   output$Receiver <- as.numeric(serial_n)
@@ -786,7 +792,8 @@ convertLotekCDMAFile <- function(file, date_format, tz) {
                 "Signal", "Sensor.Value", "Sensor.Unit")
   output <- output[, std_cols, with = FALSE]
   output$Timestamp <- fasttime::fastPOSIXct(as.character(output$Timestamp), 
-                                            tz = tz)
+                                            tz = "UTC")
+  output$Timestamp <- output$Timestamp - (gmt_cor * 3600)
 
   # final checks
   if (any(is.na(output$Timestamp))) {

diff --git a/man/convertLotekCDMAFile.Rd b/man/convertLotekCDMAFile.Rd
diff --git a/tests/testthat/test_convertLotekCDMAFile.R b/tests/testthat/test_convertLotekCDMAFile.R
@@ -12,6 +12,9 @@ Code Type:          FSK
 Serial Number:      WHS3K-1234567
 Node ID:            10000
 
+Receiver Settings:
+GMT Correction:     00:00
+
 Decoded Tag Data:
 Date      Time             TOA       Tag ID    Type     Value     Power
 =======================================================================
@@ -32,8 +35,7 @@ Date      Time      Type                    Details
 sink()
 
 test_that("convertLotekCDMAfile can read lotek cdma log files", {
-	x <- convertLotekCDMAFile(dummy_file, date_format = "%m/%d/%y", 
-                 	          tz = "Europe/Copenhagen")
+	x <- convertLotekCDMAFile(dummy_file)
 	expect_is(x, "data.table")
 })
 
@@ -50,6 +52,9 @@ Code Type:          FSK
 Serial Number:      WHS3K-1234567
 Node ID:            10000
 
+Receiver Settings:
+GMT Correction:     00:00
+
 Decoded Tag Data:
 Date      Time             TOA       Tag ID    Type     Value     Power
 =======================================================================
@@ -71,8 +76,7 @@ sink()
 
 test_that("convertLotekCDMAfile warns user if any timestamp is bad", {
 	expect_warning(
-		x <- convertLotekCDMAFile(dummy_file2, date_format = "%m/%d/%y", 
-        		                  tz = "Europe/Copenhagen"),
+		x <- convertLotekCDMAFile(dummy_file2),
         paste0("Some timestamp values are NA. This must be fixed before these ",
             "detections are used in an actel analysis."),
       fixed = TRUE)
@@ -94,6 +98,9 @@ Code Type:          FSK
 Serial Number:      WHS3K-12b67
 Node ID:            10000
 
+Receiver Settings:
+GMT Correction:     00:00
+
 Decoded Tag Data:
 Date      Time             TOA       Tag ID    Type     Value     Power
 =======================================================================
@@ -115,8 +122,7 @@ sink()
 
 test_that("convertLotekCDMAfile warns user if any receiver serial is bad", {
 	expect_warning(
-		x <- convertLotekCDMAFile(dummy_file3, date_format = "%m/%d/%y", 
-        		                  tz = "Europe/Copenhagen"),
+		x <- convertLotekCDMAFile(dummy_file3),
         paste0("Some receiver serial number values are NA. This must be fixed ",
             "before these detections are used in an actel analysis."),
       fixed = TRUE)
@@ -137,6 +143,9 @@ Code Type:
 Serial Number:      WHS3K-1234567
 Node ID:            10000
 
+Receiver Settings:
+GMT Correction:     00:00
+
 Decoded Tag Data:
 Date      Time             TOA       Tag ID    Type     Value     Power
 =======================================================================
@@ -158,8 +167,7 @@ sink()
 
 test_that("convertLotekCDMAfile warns user if code space is bad", {
     expect_warning(
-        x <- convertLotekCDMAFile(dummy_file4, date_format = "%m/%d/%y", 
-                                  tz = "Europe/Copenhagen"),
+        x <- convertLotekCDMAFile(dummy_file4),
         paste0("Some code space values are NA. This must be fixed ",
             "before these detections are used in an actel analysis."),
       fixed = TRUE)
@@ -179,6 +187,9 @@ Code Type:          FSK
 Serial Number:      WHS3K-1234567
 Node ID:            10000
 
+Receiver Settings:
+GMT Correction:     00:00
+
 Decoded Tag Data:
 Date      Time             TOA       Tag ID    Type     Value     Power
 =======================================================================
@@ -200,8 +211,7 @@ sink()
 
 test_that("convertLotekCDMAfile warns user if any signal is bad", {
     expect_warning(
-        x <- convertLotekCDMAFile(dummy_file5, date_format = "%m/%d/%y", 
-                                  tz = "Europe/Copenhagen"),
+        x <- convertLotekCDMAFile(dummy_file5),
         paste0("Some signal values are NA. This must be fixed before these ",
             "detections are used in an actel analysis."),
       fixed = TRUE)