adding a example function with regex and logging

TP/TP0_file_stats/corrections/step2.0.py

@@ -4,6 +4,9 @@ form key=val where key is p1, p2 or p3, and val is a float.
 
 """
 
+import re
+import logging
+logging.basicConfig(level=logging.INFO)
 
 def compute_stats(file_name):
     """
@@ -26,6 +29,40 @@ def compute_stats(file_name):
     return (number, total_sum, total_sum/float(number))
 
 
+def check_format_re(file_name, default_values):
+    """Check the file has the right format
+
+    :param file_name: (str) the input file name (text)
+    :param default_values: (array of float) the default values for
+                           p1, p2, and p3 respectivelly
+    :returns: the read values
+    """
+    with open(file_name) as handle:
+        for line_num, line in enumerate(handle):
+            vals = [None, None, None]
+            logging.debug("line = {}".format(line.strip()))
+            for si, sv in re.findall(r"p(\d)\s*=\s*(\d\.\d+)", line):
+                try:
+                    idx = int(si) - 1
+                except ValueError as e:
+                    logging.warning(f'file {file_name} line {line_num}: wrong format: p{si}')
+                    continue
+                if idx > 2:
+                    logging.warning(f'file {file_name} line {line_num}: p{si} out of bounds')
+                    continue
+                try:
+                    val = float(sv)
+                except ValueError as e:
+                    logging.warning(f'file {file_name} line {line_num}: wrong value: p{si}')
+                    continue
+                vals[idx] = val
+            # checking for missing item
+            for i,v in enumerate(vals):
+                if v is None:
+                    logging.warning(f'file {file_name} line {line_num}: missing: p{i+1}, setting default value')
+                    vals[i] = default_values[i-1]
+
+
 def check_format(file_name, cols_names_set):
     """
         check the file has the right format.
@@ -68,3 +105,8 @@ sums = []
 
 for file_name in file_names:
     check_format(file_name, cols_names_set)
+
+# using version with re, and type check
+print("USING VERSION WITH RE AND TYPE CHECK")
+for file_name in file_names:
+    check_format_re(file_name, [100, 200, 300])