Removed strange bug when reading .TXT smps files. Specified latin-1 encoding and relaxed error detection to ignore.

src/smog_chamber_file_reader.py

@@ -18,9 +18,11 @@ def read_txt_files_as_dict(filename : str ):
     if 'smps' in filename: 
         table_of_header = 'Sample #	Date	Start Time	Sample Temp (C)	Sample Pressure (kPa)'
         separator = '\t'
+        file_encoding = 'latin-1'
     elif 'gas' in filename:
         table_of_header = 'Date_Time	HoribaNO	HoribaNOy	Thermo42C_NO	Thermo42C_NOx	APHA370 CH4'
         separator = '\t'
+        file_encoding = 'utf-8'
     else:
         raise ValueError('intrument_folder must be set as a either "smps" or "gas"')
     
@@ -29,12 +31,13 @@ def read_txt_files_as_dict(filename : str ):
     # Read header as a dictionary and detect where data table starts
     header_dict = {}
     data_start = False    
-    with open(tmp_file_path,'r') as f:
-        file_encoding = f.encoding
+    with open(tmp_file_path,'r', encoding=file_encoding, errors='ignore') as f:
+        #file_encoding = f.encoding
         #table_preamble = ""
         table_preamble = []
-        for line_number, line in enumerate(f):   
-            
+        line_number = 0
+        for line_number, line in enumerate(f):
+            #print(line_number,line)
             if table_of_header in line:  
                 list_of_substrings = line.split(separator)              
                 data_start = True  
@@ -42,7 +45,7 @@ def read_txt_files_as_dict(filename : str ):
                 for i, name in enumerate(list_of_substrings):
                     column_names.append(str(i)+'_'+name) 
 
-                print(line_number, len(column_names ))
+                #print(line_number, len(column_names ))
                 break
             # Subdivide line into words, and join them by single space. 
             # I asumme this can produce a cleaner line that contains no weird separator characters \t \r or extra spaces and so on.