Improving readability of errors

checksit/generic.py

@@ -230,8 +230,8 @@ def check_var(dct, variable, defined_attrs, attr_rules=[], skip_spellcheck=False
                 #    print(dct["variables"][variable].get(attr_key))
                 elif not str(dct["variables"][variable].get(attr_key)) == attr_value:
                     errors.append(
-                        f"[variable**************:{variable}]: Attribute '{attr_key}' must have definition {attr_value}, "
-                        f"not {dct['variables'][variable].get(attr_key).encode('unicode_escape').decode('utf-8')}."
+                        f"[variable**************:{variable}]: Attribute '{attr_key}' must have definition '{attr_value}', "
+                        f"not '{dct['variables'][variable].get(attr_key).encode('unicode_escape').decode('utf-8')}'."
                     )
             for rule_to_check in attr_rules:
                 if rule_to_check == "rule-func:check-qc-flags":
@@ -260,8 +260,8 @@ def check_var(dct, variable, defined_attrs, attr_rules=[], skip_spellcheck=False
                     pass
                 elif not dct["variables"][variable].get(attr_key) == attr_value:
                     errors.append(
-                        f"[variable**************:{variable}]: Attribute '{attr_key}' must have definition {attr_value}, "
-                        f"not {dct['variables'][variable].get(attr_key)}."
+                        f"[variable**************:{variable}]: Attribute '{attr_key}' must have definition '{attr_value}', "
+                        f"not '{dct['variables'][variable].get(attr_key)}'."
                     )
 
     return errors, warnings
@@ -282,7 +282,7 @@ def check_file_name(file_name, vocab_checks=None, rule_checks=None, **kwargs):
     # check instrument name
     if "instrument" in vocab_checks.keys():
         if vocabs.check(vocab_checks["instrument"], file_name_parts[0], label="_") != []:
-            errors.append(f"[file name]: Invalid file name format - unknown instrument {file_name_parts[0]}")
+            errors.append(f"[file name]: Invalid file name format - unknown instrument '{file_name_parts[0]}'")
     else:
         msg = "No instrument vocab defined in specs"
         raise KeyError(msg)
@@ -303,7 +303,7 @@ def check_file_name(file_name, vocab_checks=None, rule_checks=None, **kwargs):
     # could be yyyy, yyyymm, yyyymmdd, yyyymmdd-HH, yyyymmdd-HHMM, yyyymmdd-HHMMSS
     # first checks format, then date validity
     if not date_regex.match(file_name_parts[2]):
-        errors.append(f"[file name]: Invalid file name format - bad date format {file_name_parts[2]}")
+        errors.append(f"[file name]: Invalid file name format - bad date format '{file_name_parts[2]}'")
     else:
         fmts = ("%Y", "%Y%m", "%Y%m%d", "%Y%m%d-%H", "%Y%m%d-%H%M", "%Y%m%d-%H%M%S")
         valid_date_found = False
@@ -315,20 +315,20 @@ def check_file_name(file_name, vocab_checks=None, rule_checks=None, **kwargs):
             except ValueError:
                 pass
         if not valid_date_found:
-            errors.append(f"[file name]: Invalid file name format - invalid date in file name {file_name_parts[2]}")
+            errors.append(f"[file name]: Invalid file name format - invalid date in file name '{file_name_parts[2]}'")
 
     # check data product
     if "data_product" in vocab_checks.keys():
         if vocabs.check(vocab_checks["data_product"], file_name_parts[3], label="_") != []:
-            errors.append(f"[file name]: Invalid file name format - unknown data product {file_name_parts[3]}")
+            errors.append(f"[file name]: Invalid file name format - unknown data product '{file_name_parts[3]}'")
     else:
         msg = "No data product vocab defined in specs"
         raise KeyError(msg)
 
     # check version number format
     version_component = file_name_parts[-1].split(".nc")[0]
     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}")
+        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
     if len(file_name_parts) > 8:

checksit/rules/rule_funcs.py

@@ -299,10 +299,10 @@ def ncas_platform(value, context, extras=None, label=""):
 
     if value not in ncas_platforms:
         errors.append(f"{label} '{value}' is not a valid NCAS platform")
-    
+
     return errors
 
-        
+
 def check_qc_flags(value, context, extras=None, label=""):
     """
     A function to check flag_values and flag_meanings
@@ -315,7 +315,7 @@ def check_qc_flags(value, context, extras=None, label=""):
 
     # check flag_values are correctly formatted (should be array of bytes)
     if not (isinstance(value, np.ndarray) or isinstance(value, tuple)):
-        errors.append(f"{label} QC flag_values must be an array or tuple of byte values, not {type(value)}.")
+        errors.append(f"{label} QC flag_values must be an array or tuple of byte values, not '{type(value)}'.")
 
     # check there are at least two values and they start with 0 and 1
     if not len(value) > 2:

checksit/rules/rules.py

@@ -20,25 +20,78 @@ def __init__(self):
                  "(not applicable)|(not available)"
 
         self.static_regex_rules = {
-            "integer": r"-?\d+",
-            "valid-email": r"[^@\s]+@[^@\s]+\.[^\s@]+",
-            "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": r"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?",
-            "datetime-or-na": 
-                 r"(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?)|" + _NOT_APPLICABLE_RULES,
-            "number": r"-?\d+(\.\d+)?",
-            "location": r'(.)+(\,\ )(.)+',
-            "latitude-image": r'[\+|\-]?[0-9]{1,2}\.[0-9]{0,6}',
-            "longitude-image": r'[\+|\-]?1?[0-9]{1,2}\.[0-9]{0,6}',
-            "title": r'(.)+_(.)+_([1-2][0-9][0-9][0-9])([0][0-9]|[1][0-2])?([0-2][0-9]|[3][0-1])?-?([0-1][0-9]|[2][0-3])?([0-5][0-9])?([0-5][0-9])?(_.+)?_v([0-9]+)\.([0-9]+)\.(png|PNG|jpg|JPG|jpeg|JPEG)',
-            "title-data-product": r'(.)+_(.)+_([1-2][0-9][0-9][0-9])([0][0-9]|[1][0-2])?([0-2][0-9]|[3][0-1])?-?([0-1][0-9]|[2][0-3])?([0-5][0-9])?([0-5][0-9])?_(plot|photo)((.)+)?_v([0-9]+)\.([0-9]+)\.(png|PNG|jpg|JPG|jpeg|JPEG)',
-            "name-format": r'([^,])+, ([^,])+( ?[^,]+|((.)\.))',
-            "name-characters": r'[A-Za-z_À-ÿ\-\'\ \.\,]+',
-            "altitude-image-warning": r'-?\d+\sm',    # should be integers only for images
-            "altitude-image": r'-?\d+(\.\d+)?\sm',
-            "ncas-email": r'[^@\s][email protected]'
+            "integer": {
+                "regex-rule": r"-?\d+",
+                "example": "10"
+            },
+            "valid-email": {
+                "regex-rule": r"[^@\s]+@[^@\s]+\.[^\s@]+",
+                "example": "[email protected]"
+            },
+            "valid-url": {
+                "regex-rule": r"https?://[^\s]+\.[^\s]*[^\s\.](/[^\s]+)?",
+                "example": "https://github.com"
+            },
+            "valid-url-or-na": {
+                "regex-rule": r"(https?://[^\s]+\.[^\s]*[^\s\.](/[^\s]+)?)|" + _NOT_APPLICABLE_RULES,
+                "example": "https://github.com"
+            },
+            "match:vN.M": {
+                "regex-rule": r"v\d\.\d",
+                "example": "v1.0"
+            },
+            "datetime": {
+                "regex-rule": r"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?",
+                "example": "2023-11-17T15:00:00"
+            },
+            "datetime-or-na": {
+                 "regex-rule": r"(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?)|" + _NOT_APPLICABLE_RULES,
+                 "example": "2023-11-17T15:00:00"
+            },
+            "number": {
+                "regex-rule": r"-?\d+(\.\d+)?",
+                "example": "10.5"
+            },
+            "location": {
+                "regex-rule": r'(.)+(\,\ )(.)+',
+                "example": "Chilbolton Atmospheric Observatory, Chilbolton, Hampshire, UK"
+            },
+            "latitude-image": {
+                "regex-rule": r'[\+|\-]?[0-9]{1,2}\.[0-9]{0,6}',
+                "example": "12.345678"
+            },
+            "longitude-image": {
+                "regex-rule": r'[\+|\-]?1?[0-9]{1,2}\.[0-9]{0,6}',
+                "example": "123.456789"
+            },
+            "title": {
+                "regex-rule": r'(.)+_(.)+_([1-2][0-9][0-9][0-9])([0][0-9]|[1][0-2])?([0-2][0-9]|[3][0-1])?-?([0-1][0-9]|[2][0-3])?([0-5][0-9])?([0-5][0-9])?(_.+)?_v([0-9]+)\.([0-9]+)\.(png|PNG|jpg|JPG|jpeg|JPEG)',
+                "example": "ncas-cam-9_cao_20210623-215001_v1.0.jpg"
+            },
+            "title-data-product": {
+                "regex-rule": r'(.)+_(.)+_([1-2][0-9][0-9][0-9])([0][0-9]|[1][0-2])?([0-2][0-9]|[3][0-1])?-?([0-1][0-9]|[2][0-3])?([0-5][0-9])?([0-5][0-9])?_(plot|photo)((.)+)?_v([0-9]+)\.([0-9]+)\.(png|PNG|jpg|JPG|jpeg|JPEG)',
+                "example": "ncas-cam-9_cao_20210623-215001_photo_v1.0.jpg"
+            },
+            "name-format": {
+                "regex-rule": r'([^,])+, ([^,])+( ?[^,]+|((.)\.))',
+                "example": "Jones, Sam"
+            },
+            "name-characters": {
+                "regex-rule": r'[A-Za-z_À-ÿ\-\'\ \.\,]+',
+                "example": "Jones, Sam"
+            },
+            "altitude-image-warning": {
+                "regex-rule": r'-?\d+\sm',    # should be integers only for images
+                "example": "123 m"
+            },
+            "altitude-image": {
+                "regex-rule": r'-?\d+(\.\d+)?\sm',
+                "example": "123.45 m"
+            },
+            "ncas-email": {
+                "regex-rule": r'[^@\s][email protected]',
+                "example": "[email protected]"
+            }
         }
 
     def _map_type_rule(self, type_rule):
@@ -87,10 +140,10 @@ def check(self, rule_lookup, value, context=None, label=""):
                 regex_rule = i.split(":", 1)[1]
 
                 if regex_rule in self.static_regex_rules:
-                    pattern = self.static_regex_rules[regex_rule]
+                    pattern = self.static_regex_rules[regex_rule]["regex-rule"]
 
                     if not re.match("^" + pattern + "$", value):
-                        output.append(f"{label} Value '{value}' does not match regex rule: '{regex_rule}'.")
+                        output.append(f"{label} Value '{value}' does not match regex rule: '{regex_rule}' - Example valid value '{self.static_regex_rules[regex_rule]['example']}'.")
 
                 else:
                     raise Exception(f"Regex rule not found with rule ID: {i}.")

tests/test_generic.py

@@ -311,13 +311,13 @@ def test_check_var():
     variable = "var2"
     defined_attrs = ["long_name:Variable 2", "units:s"]
     errors, warnings = cg.check_var(dct, variable, defined_attrs, skip_spellcheck=True)
-    assert errors == ["[variable**************:var2]: Attribute 'units' must have definition s, not kg."]
+    assert errors == ["[variable**************:var2]: Attribute 'units' must have definition 's', not 'kg'."]
     assert warnings == []
 
     variable = "var2:__OPTIONAL__"
     defined_attrs = ["long_name:Variable 2", "units:s"]
     errors, warnings = cg.check_var(dct, variable, defined_attrs, skip_spellcheck=True)
-    assert errors == ["[variable**************:var2]: Attribute 'units' must have definition s, not kg."]
+    assert errors == ["[variable**************:var2]: Attribute 'units' must have definition 's', not 'kg'."]
     assert warnings == []
 
     # Test that the function correctly handles badly formatted flag_values
@@ -354,7 +354,7 @@ def test_check_file_name():
     }
     file_name = "inst3_plat1_20220101_prod1_v1.0.nc"
     errors, warnings = cg.check_file_name(file_name, vocab_checks, rule_checks)
-    assert errors == ["[file name]: Invalid file name format - unknown instrument inst3"]
+    assert errors == ["[file name]: Invalid file name format - unknown instrument 'inst3'"]
     assert warnings == []
 
     # Test that the function correctly identifies invalid platform name
@@ -366,25 +366,25 @@ def test_check_file_name():
     # Test that the function correctly identifies invalid date format
     file_name = "inst1_plat1_2022010_prod1_v1.0.nc"
     errors, warnings = cg.check_file_name(file_name, vocab_checks, rule_checks)
-    assert errors == ["[file name]: Invalid file name format - bad date format 2022010"]
+    assert errors == ["[file name]: Invalid file name format - bad date format '2022010'"]
     assert warnings == []
 
     # Test that the function correctly identifies invalid date
     file_name = "inst1_plat1_20221301_prod1_v1.0.nc"
     errors, warnings = cg.check_file_name(file_name, vocab_checks, rule_checks)
-    assert errors == ["[file name]: Invalid file name format - invalid date in file name 20221301"]
+    assert errors == ["[file name]: Invalid file name format - invalid date in file name '20221301'"]
     assert warnings == []
 
     # Test that the function correctly identifies invalid data product
     file_name = "inst1_plat1_20220101_prod3_v1.0.nc"
     errors, warnings = cg.check_file_name(file_name, vocab_checks, rule_checks)
-    assert errors == ["[file name]: Invalid file name format - unknown data product prod3"]
+    assert errors == ["[file name]: Invalid file name format - unknown data product 'prod3'"]
     assert warnings == []
 
     # Test that the function correctly identifies invalid version number format
     file_name = "inst1_plat1_20220101_prod1_v10.nc"
     errors, warnings = cg.check_file_name(file_name, vocab_checks, rule_checks)
-    assert errors == ["[file name]: Invalid file name format - incorrect file version number v10"]
+    assert errors == ["[file name]: Invalid file name format - incorrect file version number 'v10'"]
     assert warnings == []
 
     # Test that the function correctly identifies too many options in file name
@@ -396,7 +396,7 @@ def test_check_file_name():
     # Test that the function correctly handles multiple errors
     file_name = "inst3_plat3_20220101_prod1_v1.0.nc"
     errors, warnings = cg.check_file_name(file_name, vocab_checks, rule_checks)
-    assert errors == ["[file name]: Invalid file name format - unknown instrument inst3","[file name]: Invalid file name format - 'plat3' must be one of: '['plat1', 'plat2']'"]
+    assert errors == ["[file name]: Invalid file name format - unknown instrument 'inst3'","[file name]: Invalid file name format - 'plat3' must be one of: '['plat1', 'plat2']'"]
     assert warnings == []
 
     # Test that the function correctly handles valid file names

tests/test_images.py

@@ -59,7 +59,7 @@ def test_other_plot_checks(plot, error_level, number_errors):
         ("nerc-mstrf-radar-mst_capel-dewi_20230809_st300_wind.png",
             (
                 "[global-attributes:******:XMP-dc:Title]*** Value 'nerc-mstrf-radar-mst_capel-dewi_20230809_st300_wind.png'"
-                " does not match regex rule: 'title'."
+                " does not match regex rule: 'title' - Example valid value 'ncas-cam-9_cao_20210623-215001_v1.0.jpg'."
             ),
         ),
         ("nerc-mstrf-met-sensors_capel-dewi_20160906_campbell-sci.png",