Merge branch 'main' into dependabot/pip/pip-48da786093

cfpb · Jun 18, 2024 · 6397a8f · 6397a8f
2 parents b9ec1c5 + 1b08fe6
commit 6397a8f
Show file tree

Hide file tree

Showing 4 changed files with 17 additions and 14 deletions.
diff --git a/poetry.lock b/poetry.lock
diff --git a/src/regtech_data_validator/cli.py b/src/regtech_data_validator/cli.py
@@ -96,12 +96,8 @@ def validate(
         status = 'FAILURE'
         findings_df = validation_results.findings
         no_of_findings = len(findings_df.index.unique())
-        total_errors = sum(
-            [
-                validation_results.error_counts.total_count,
-                validation_results.warning_counts.total_count,
-            ]
-        )
+        warning_count = validation_results.warning_counts.total_count
+        error_count = validation_results.error_counts.total_count
 
         match output:
             case OutputFormat.PANDAS:
@@ -113,7 +109,7 @@ def validate(
             case OutputFormat.TABLE:
                 print(df_to_table(findings_df))
             case OutputFormat.DOWNLOAD:
-                print(df_to_download(findings_df, total_errors))
+                print(df_to_download(findings_df, warning_count, error_count))
             case _:
                 raise ValueError(f'output format "{output}" not supported')
 

diff --git a/src/regtech_data_validator/data_formatters.py b/src/regtech_data_validator/data_formatters.py
@@ -23,7 +23,7 @@ def find_check(group_name, checks):
     return next(gen)
 
 
-def df_to_download(df: pd.DataFrame, total_errors: int, max_errors: int = 1000000) -> str:
+def df_to_download(df: pd.DataFrame, warning_count: int = 0, error_count: int = 0, max_errors: int = 1000000) -> str:
     header = "validation_type,validation_id,validation_name,row,unique_identifier,fig_link,validation_description,"
     if df.empty:
         # return headers of csv for 'emtpy' report
@@ -106,8 +106,16 @@ def df_to_download(df: pd.DataFrame, total_errors: int, max_errors: int = 100000
             field_headers.append(f"value_{i+1}")
         header += ",".join(field_headers) + "\n"
 
+        total_errors = warning_count + error_count
+        error_type = "errors"
+        if warning_count > 0:
+            if error_count > 0:
+                error_type = "errors and warnings"
+            else:
+                error_type = "warnings"
+
         if total_errors and total_errors > max_errors:
-            header += f"The submission contained {total_errors}, but only {max_errors} will be displayed in the download report.  Fix the current errors and resubmit to see more.\n"
+            header += f"Your register contains {total_errors} {error_type}, however, only {max_errors} records are displayed in this report. To see additional {error_type}, correct the listed records, and upload a new file.\n"
 
         csv_data = header + total_csv
         return csv_data

diff --git a/tests/test_output_formats.py b/tests/test_output_formats.py
@@ -255,14 +255,14 @@ def test_download_csv(self):
             ","uid","12345678901234567890"
             """
         ).strip('\n')
-        actual_output = df_to_download(self.input_df, 2)
+        actual_output = df_to_download(self.input_df, error_count=2)
         assert actual_output.strip() == expected_output
 
     def test_download_max_message_csv(self):
         expected_output = dedent(
             """
             validation_type,validation_id,validation_name,row,unique_identifier,fig_link,validation_description,field_1,value_1,field_2,value_2
-            The submission contained 5, but only 3 will be displayed in the download report.  Fix the current errors and resubmit to see more.
+            Your register contains 6 errors and warnings, however, only 3 records are displayed in this report. To see additional errors and warnings, correct the listed records, and upload a new file.
             "Error","E2008","amount_approved.conditional_field_conflict",4,"12345678901234567891","https://www.consumerfinance.gov/data-research/small-business-lending/filing-instructions-guide/2024-guide/#4.2.7","* When 'action taken' does **not** equal 1 (originated) or 
             2 (approved but not accepted), 'amount approved or originated' must be blank.
             * When 'action taken' equals 1 or 2, 'amount approved or originated' must **not** be blank.
@@ -275,7 +275,7 @@ def test_download_max_message_csv(self):
             ","uid","12345678901234567890"
             """
         ).strip('\n')
-        actual_output = df_to_download(self.input_df, 5, 3)
+        actual_output = df_to_download(self.input_df, warning_count=1, error_count=5, max_errors=3)
         assert actual_output.strip() == expected_output
 
     def test_empty_download_csv(self):
@@ -284,5 +284,5 @@ def test_empty_download_csv(self):
             validation_type,validation_id,validation_name,row,unique_identifier,fig_link,validation_description,
             """
         ).strip('\n')
-        actual_output = df_to_download(pd.DataFrame(), 0)
+        actual_output = df_to_download(pd.DataFrame(), warning_count=0, error_count=0)
         assert actual_output == expected_output