Use raw strings to avoid 'invalid escape sequence' warnings in regex

checksit/generic.py

@@ -8,7 +8,7 @@
 
 # date formate regex
 # could be yyyy, yyyymm, yyyymmdd, yyyymmdd-HH, yyyymmdd-HHMM, yyyymmdd-HHMMSS
-date_regex = re.compile("^\d{4}$|^\d{6}$|^\d{8}$|^\d{8}-\d{2}$|^\d{8}-\d{4}$|^\d{8}-\d{6}$")
+date_regex = re.compile(r"^\d{4}$|^\d{6}$|^\d{8}$|^\d{8}-\d{2}$|^\d{8}-\d{4}$|^\d{8}-\d{6}$")
 
 def _get_bounds_var_ids(dct):
     return [var_id for var_id in dct["variables"] if (
@@ -313,7 +313,7 @@ def check_file_name(file_name, vocab_checks=None, **kwargs):
 
     # check version number format
     version_component = file_name_parts[-1].split(".nc")[0]
-    if not re.match("^v\d.\d$", version_component):
+    if not re.match(r"^v\d.\d$", version_component):
         errors.append(f"[file name]: Invalid file name format - incorrect file version number {version_component}")
 
     # check number of options - max length of splitted file name

checksit/make_specs.py

@@ -51,14 +51,14 @@ def make_amof_specs(version_number):
         elif compliance.lower() == "valid url _or_ n/a":
             rule = "regex-rule:valid-url-or-na"
         elif "match: " in compliance.lower():
-            if 'YYYY-MM-DDThh:mm:ss\.\d+ _or_ N/A' in compliance:
+            if r'YYYY-MM-DDThh:mm:ss\.\d+ _or_ N/A' in compliance:
                 rule = "regex-rule:datetime-or-na"
             elif 'vN.M' in compliance:
                 rule = "regex-rule:match:vN.M"
-            elif 'YYYY-MM-DDThh:mm:ss\.\d+' in compliance:
+            elif r'YYYY-MM-DDThh:mm:ss\.\d+' in compliance:
                 rule = "regex-rule:datetime"
             elif '<number> m' in compliance:
-                rule = "regex:^-?\d+\.?\d* m$"
+                rule = r"regex:^-?\d+\.?\d* m$"
             else:
                 rule = f"regex-rule:EDIT:{compliance}"
         elif compliance.lower() in ["number","integer","int","float","string","str"]:
@@ -88,9 +88,9 @@ def make_amof_specs(version_number):
             rule = f"rule-func:match-one-of:{options}"
         else:
             rule = f"UNKNOWN compliance: {compliance}"
-        rule = rule.replace('(','\(')
-        rule = rule.replace(')','\)')
-        rule = [ rule.replace(' ','\s') if "regex:" in rule else rule ][0]
+        rule = rule.replace('(',r'\(')
+        rule = rule.replace(')',r'\)')
+        rule = [ rule.replace(' ',r'\s') if "regex:" in rule else rule ][0]
         attr_rules[attr] = rule
 
 
@@ -205,11 +205,11 @@ def make_amof_specs(version_number):
                     elif compliance.lower() == "valid url _or_ n/a":
                         rule = "regex-rule:valid-url-or-na"
                     elif "match: " in compliance.lower():
-                        if 'YYYY-MM-DDThh:mm:ss\.\d+ _or_ N/A' in compliance:
+                        if r'YYYY-MM-DDThh:mm:ss\.\d+ _or_ N/A' in compliance:
                             rule = "regex-rule:datetime-or-na"
                         elif 'vN.M' in compliance:
                             rule = "regex-rule:match:vN.M"
-                        elif 'YYYY-MM-DDThh:mm:ss\.\d+' in compliance:
+                        elif r'YYYY-MM-DDThh:mm:ss\.\d+' in compliance:
                             rule = "regex-rule:datetime"
                         else:
                             rule = f"regex-rule:EDIT:{compliance}"
@@ -232,9 +232,9 @@ def make_amof_specs(version_number):
                         rule = f"rule-func:match-one-of:{options}"
                     else:
                         rule = f"UNKNOWN compliance: {compliance}"
-                    rule = rule.replace('(','\(')
-                    rule = rule.replace(')','\)')
-                    rule = [ rule.replace(' ','\s') if "regex:" in rule else rule ][0]
+                    rule = rule.replace('(',r'\(')
+                    rule = rule.replace(')',r'\)')
+                    rule = [ rule.replace(' ',r'\s') if "regex:" in rule else rule ][0]
                     attr_rules[attr] = rule
             prod_attrs_exist = True
         else:

checksit/readers/cdl.py

@@ -76,7 +76,7 @@ def _get_sections(self, lines, split_patterns, start_at):
                 if split_patterns:
                     splitter = split_patterns.popleft()
             else:
-                line_no_comments = re.split(";\s+//.*$", line)[0].strip().rstrip(";").strip()
+                line_no_comments = re.split(r";\s+//.*$", line)[0].strip().rstrip(";").strip()
                 if not line_no_comments.startswith("//"):
                     current.append(line_no_comments)
 

checksit/rules/rule_funcs.py

@@ -71,7 +71,7 @@ def string_of_length(value, context, extras=None, label=""):
     Matches string of length...
     """
     spec = extras[0]
-    min_length = int(re.match("^(\d+)\+?", spec).groups()[0])
+    min_length = int(re.match(r"^(\d+)\+?", spec).groups()[0])
 
     errors = []
 

checksit/rules/rules.py

@@ -25,9 +25,9 @@ def __init__(self):
             "valid-url": r"https?://[^\s]+\.[^\s]*[^\s\.](/[^\s]+)?",
             "valid-url-or-na": r"(https?://[^\s]+\.[^\s]*[^\s\.](/[^\s]+))|" + _NOT_APPLICABLE_RULES,
             "match:vN.M": r"v\d\.\d",
-            "datetime": "\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?",
+            "datetime": r"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?",
             "datetime-or-na": 
-                 "(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?)|" + _NOT_APPLICABLE_RULES,
+                 r"(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?)|" + _NOT_APPLICABLE_RULES,
             "number": r"-?\d+(\.\d+)?"
         }
 

checksit/summary.py

@@ -58,7 +58,7 @@ def summarise(log_files=None, log_directory=None, show_files=False,
 
     for filename in log_files:
         df = pd.read_csv(filename, sep=sep, index_col=None, header=None, names=headers)
-        df = df.replace({"^\s*|\s*$":""}, regex=True)
+        df = df.replace({r"^\s*|\s*$":""}, regex=True)
         df["logfile"] = os.path.basename(filename)
         count += len(df)
         li.append(df)