allow µ in sequence line items

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: isoreader
 Title: Read Stable Isotope Data Files
 Description: Interface to the raw data file formats commonly encountered in scientific disciplines that make use of stable isotopes.
-Version: 1.4.1
+Version: 1.4.2
 Authors@R: 
     c(person(
         given = "Sebastian", family = "Kopf", 

R/utils_binary_isodat_files.R

@@ -793,23 +793,34 @@ parse_raw_data <- function(raw, type, n = full_raw(), ignore_trailing_zeros = FA
     regexp <- sprintf("(%s){%.0f}", dbc[[1]]$regexp, n)
     if (length(grepRaw(regexp, raw_trim)) == 0) {
       # something that is NOT text is in the raw_trim
-      non_text_pos <- grepRaw("([\x20-\xff][\x01-\xff])|(\\x00\\x00)", raw_trim)
-      actual_text <- intToUtf8(raw_trim[1:(non_text_pos - 1)])
-      if (!is.null(errors)) {
-        err_raw <- raw_trim[(non_text_pos + 1):length(raw_trim)]
-        stop(
-          sprintf("%sexpected unicode data for %.0f bytes but found only %.0f ('%s'), non-text raw data afterwards: %s", 
-                  error_prefix, n*2, non_text_pos, actual_text, 
-                  if (length(err_raw) > 10) 
-                    c(as.character(head(err_raw, 10)), sprintf("+%d more", length(err_raw) - 10)) |>
-                    paste(collapse = " ")
-                  else 
-                    as.character(err_raw) |>
-                    paste(collapse = " ")
-          ), 
-          call. = FALSE)
+
+      # check for common extended unicode characters (micro)
+      ext_uni <- grepRaw("\xb5\xff", raw_trim)
+      if (length(ext_uni) > 0L) {
+        raw_trim[ext_uni + 1L] <- as.raw(00)
+        raw[ext_uni + 1L] <- as.raw(00)
+      }
+
+      # check again if any extended unicodes were found
+      if (length(ext_uni) == 0L || length(grepRaw(regexp, raw_trim)) == 0) {
+        non_text_pos <- grepRaw("([\x20-\xff][\x01-\xff])|(\\x00\\x00)", raw_trim)
+        actual_text <- intToUtf8(raw_trim[1:(non_text_pos - 1)])
+        if (!is.null(errors)) {
+          err_raw <- raw_trim[(non_text_pos + 1):length(raw_trim)]
+          stop(
+            sprintf("%sexpected unicode data for %.0f bytes but found only %.0f ('%s'), non-text raw data afterwards: %s", 
+                    error_prefix, n*2, non_text_pos, actual_text, 
+                    if (length(err_raw) > 10) 
+                      c(as.character(head(err_raw, 10)), sprintf("+%d more", length(err_raw) - 10)) |>
+                      paste(collapse = " ")
+                    else 
+                      as.character(err_raw) |>
+                      paste(collapse = " ")
+            ), 
+            call. = FALSE)
+        }
+        return(NULL)
       }
-      return(NULL)
     }
   }
 

tests/testthat/test-continuous-flow.R

@@ -319,6 +319,28 @@ test_that("test that additional continous flow files can be read", {
       `Rps 46CO2/44CO2` = NA)
   )
 
+  check_continuous_flow_test_file(
+    "dxf_example_C_02.dxf",
+    c("file_id", "file_root", "file_path", "file_subpath", "file_datetime", 
+      "file_size", "Row", "Peak Center", "Check Ref. Dilution", "H3 Stability", 
+      "H3 Factor", "AS Sample", "AS Method", "Identifier 1", "Identifier 2", 
+      "Analysis", "Comment", "Preparation", "Method", "measurement_info", 
+      "MS_integration_time.s"),
+    15,
+    c(Nr. = NA, Start = "s", Rt = "s", End = "s", `Ampl 44` = "mV", `Ampl 45` = "mV", 
+      `Ampl 46` = "mV", `BGD 44` = "mV", `BGD 45` = "mV", `BGD 46` = "mV",
+      `rIntensity 44` = "mVs", `rIntensity 45` = "mVs", `rIntensity 46` = "mVs", 
+      `rIntensity All` = "mVs", `Intensity 44` = "Vs", `Intensity 45` = "Vs", 
+      `Intensity 46` = "Vs", `Intensity All` = "Vs", 
+      `Sample Dilution` = "%", `List First Peak` = NA, `rR 45CO2/44CO2` = NA, 
+      `rR 46CO2/44CO2` = NA, `Is Ref.?` = NA, `R 45CO2/44CO2` = NA, `Ref. Name` = NA, 
+      `rd 45CO2/44CO2` = "permil", `d 45CO2/44CO2` = "permil", `R 46CO2/44CO2` = NA, 
+      `rd 46CO2/44CO2` = "permil", `d 46CO2/44CO2` = "permil", `R 13C/12C` = NA, 
+      `d 13C/12C` = "permil", `AT% 13C/12C` = "%", `R 18O/16O` = NA, `d 18O/16O` = "permil", 
+      `AT% 18O/16O` = "%", `R 17O/16O` = NA, `d 17O/16O` = NA, `Rps 45CO2/44CO2` = NA, 
+      `Rps 46CO2/44CO2` = NA)
+  )
+
   check_continuous_flow_test_file(
     "dxf_example_CNS_01.dxf",
     c("file_id", "file_root", "file_path", "file_subpath", "file_datetime",