Fixed #496 - Better error handling for gen_license

 * Produce error message for `gen-license` if no `license_expression` is
in the input

Signed-off-by: Chin Yeung Li <[email protected]>

Author: chinyeungli

src/attributecode/cmd.py

@@ -323,13 +323,17 @@ def gen_license(location, output, djc, scancode, verbose):
     api_key = ''
     errors = []
 
+    log_file_loc = os.path.join(output, 'error.log')
+
     if location.endswith('.csv') or location.endswith('.json') or location.endswith('.xlsx'):
-        abouts = collect_inventory_license_expression(location=location, scancode=scancode)
+        errors, abouts = collect_inventory_license_expression(location=location, scancode=scancode)
+        if errors:
+            severe_errors_count = report_errors(errors, quiet=False, verbose=verbose, log_file_loc=log_file_loc)
+            sys.exit(severe_errors_count)
     else:
         #_errors, abouts = collect_inventory(location)
         errors, abouts = collect_abouts_license_expression(location)
 
-    log_file_loc = os.path.join(output, 'error.log')
     if djc:
         # Strip the ' and " for api_url, and api_key from input
         api_url = djc[0].strip("'").strip('"')

src/attributecode/model.py

@@ -1402,20 +1402,31 @@ def collect_inventory_license_expression(location, scancode=False):
     validation. The purpose of this is to speed up the process for `gen_license` command.
     """
     abouts = []
+    errors = []
+
     if scancode:
         inventory = gen.load_scancode_json(location)
+        # ScanCode is using 'license_expressions' whereas we are using 'license_expression'
+        if not 'license_expressions' in inventory[0]:
+            errors.append(Error(CRITICAL, "No 'license_expressions' field in the input."))
+            return errors, abouts
     else:
         if location.endswith('.csv'):
             inventory = gen.load_csv(location)
         elif location.endswith('.xlsx'):
             _dup_cols_err, inventory = gen.load_excel(location)
         else:
             inventory = gen.load_json(location)
+        # Check if 'license_expression' field is in the input
+        if not 'license_expression' in inventory[0]:
+            errors.append(Error(CRITICAL, "No 'license_expression' field in the input."))
+            return errors, abouts
+
     for data in inventory:
         about = About()
         about.load_dict(data, base_dir='', scancode=scancode)
         abouts.append(about)
-    return abouts
+    return errors, abouts
 
 
 def get_field_names(abouts):
@@ -1735,6 +1746,7 @@ def pre_process_and_fetch_license_dict(abouts, api_url=None, api_key=None, scanc
                         key_text_dict[lic_key] = detail_list
                 if not about.license_key.value:
                     about.license_key.value = lic_list
+
     return key_text_dict, errors
 
 

src/attributecode/util.py

@@ -266,7 +266,7 @@ def load_csv(location):
                      errors='replace') as csvfile:
         for row in csv.DictReader(csvfile):
             # convert all the column keys to lower case
-            updated_row = {key.lower(): value for key, value in row.items()}
+            updated_row = {key.lower().strip(): value for key, value in row.items()}
             results.append(updated_row)
     return results