Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update validation and return message #61

Merged
merged 2 commits into from
Jul 25, 2024
Merged

Update validation and return message #61

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
94cfa3d
Add Issues column as a first column
rjambrecic Jul 25, 2024
fc9a9c4
Update response message if dataframe contains Issues column
rjambrecic Jul 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion google_sheets/app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -392,9 +392,10 @@ async def process_data(
target_resource, # type: ignore
)

issues_present = "Issues" in validated_df.columns
values = [validated_df.columns.tolist(), *validated_df.values.tolist()]

return GoogleSheetValues(values=values)
return GoogleSheetValues(values=values, issues_present=issues_present)


async def process_campaigns_and_ad_groups(
Expand Down Expand Up @@ -544,5 +545,8 @@ async def process_spreadsheet(
sheet_values=processed_values,
)
response += f"Sheet with the name '{title}' has been created successfully.\n"
if processed_values.issues_present:
response += """But there are issues present in the data.
Please check the 'Issues' column and correct the data accordingly.\n\n"""

return response
3 changes: 2 additions & 1 deletion google_sheets/data_processing/processing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,8 @@ def process_data_f(


def _validate_output_data_ad(df: pd.DataFrame) -> pd.DataFrame: # noqa: C901
df["Issues"] = ""
df.insert(0, "Issues", "")

headline_columns = [col for col in df.columns if "Headline" in col]
description_columns = [col for col in df.columns if "Description" in col]

Expand Down
5 changes: 5 additions & 0 deletions google_sheets/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,3 +7,8 @@ class GoogleSheetValues(BaseModel):
values: List[List[Any]] = Field(
..., title="Values", description="Values to be written to the Google Sheet."
)
issues_present: bool = Field(
default=False,
title="Issues Present",
description="Whether any issues are present.",
)
112 changes: 111 additions & 1 deletion tests/app/test_app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,7 +294,7 @@ class TestProcessData:
],
)
@pytest.mark.asyncio()
async def test_process_data(
async def test_process_data_keywords(
self,
template_sheet_values: GoogleSheetValues,
new_campaign_sheet_values: GoogleSheetValues,
Expand Down Expand Up @@ -328,6 +328,116 @@ async def test_process_data(
)
assert detail in exc.value.detail

@pytest.mark.asyncio()
async def test_process_data_ads(self) -> None:
template_sheet_values = GoogleSheetValues(
values=[
[
"Final URL",
"Headline 1",
"Headline 2",
"Headline 3",
"Description Line 1",
"Description Line 2",
"Path 1",
"Path 2",
],
[
"https://www.example.com/from",
"H" * 31,
"Headline 2",
"Headline 3",
"Description Line 1",
"Description Line 2",
"Path 1",
"Path 2",
],
]
)
new_campaign_sheet_values = GoogleSheetValues(
values=[
[
"Country",
"Station From",
"Station To",
"Final Url From",
"Final Url To",
],
[
"India",
"Delhi",
"Mumbai",
"https://www.example.com/from",
"https://www.example.com/to",
],
]
)
merged_campaigns_ad_groups_df = pd.DataFrame(
{
"Campaign Name": [
"INSERT_COUNTRY - INSERT_STATION_FROM - INSERT_STATION_TO"
],
"Ad Group Name": ["INSERT_STATION_FROM - INSERT_STATION_TO"],
"Match Type": ["Exact"],
}
)
result = await process_data(
template_sheet_values=template_sheet_values,
new_campaign_sheet_values=new_campaign_sheet_values,
merged_campaigns_ad_groups_df=merged_campaigns_ad_groups_df,
target_resource="ad",
)

expected = GoogleSheetValues(
values=[
[
"Issues",
"Campaign Name",
"Ad Group Name",
"Match Type",
"Final URL",
"Headline 1",
"Headline 2",
"Headline 3",
"Description Line 1",
"Description Line 2",
"Path 1",
"Path 2",
],
[
"Headline length should be less than 30 characters, found 31 in column Headline 1.\n",
"India - Delhi - Mumbai",
"Delhi - Mumbai",
"Exact",
"https://www.example.com/from",
"HHHHHHHHHHHHHHHHHHHHHHHHHHHHHHH",
"Headline 2",
"Headline 3",
"Description Line 1",
"Description Line 2",
"Path 1",
"Path 2",
],
[
"Headline length should be less than 30 characters, found 31 in column Headline 1.\n",
"India - Delhi - Mumbai",
"Mumbai - Delhi",
"Exact",
"https://www.example.com/to",
"HHHHHHHHHHHHHHHHHHHHHHHHHHHHHHH",
"Headline 2",
"Headline 3",
"Description Line 1",
"Description Line 2",
"Path 1",
"Path 2",
],
],
issues_present=True,
)

assert result.model_dump() == expected.model_dump()


class TestOpenAPIJSON:
def test_openapi(self) -> None:
Expand Down
64 changes: 42 additions & 22 deletions tests/data_processing/test_processing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,33 +167,53 @@ def test_process_data_f(


@pytest.mark.parametrize(
"issues_column",
("df", "issues_column"),
[
[
"Duplicate headlines found.\nDuplicate descriptions found.\n",
"Duplicate descriptions found.\n",
"",
"Minimum 3 headlines are required, found 2.\nMinimum 2 descriptions are required, found 1.\nHeadline length should be less than 30 characters, found 31 in column Headline 2.\n",
],
None,
(
pd.DataFrame(
{
"Headline 1": ["H1", "H1", "H1", "H1"],
"Headline 2": ["H1", "H2", "H2", ("H" * 31)],
"Headline 3": ["H3", "H3", "H3", ""],
"Description 1": ["D1", "D1", "D2", "D3"],
"Description 2": ["D1", "D1", "D3", ""],
"Path 1": ["P1", "P1", "P1", "P1"],
"Path 2": ["P2", "P2", "P2", "P2"],
"Final URL": ["URL", "URL", "URL", "URL"],
}
),
[
"Duplicate headlines found.\nDuplicate descriptions found.\n",
"Duplicate descriptions found.\n",
"",
"Minimum 3 headlines are required, found 2.\nMinimum 2 descriptions are required, found 1.\nHeadline length should be less than 30 characters, found 31 in column Headline 2.\n",
],
),
(
pd.DataFrame(
{
"Headline 1": ["H1", "H1", "H1", "H1"],
"Headline 2": ["H2", "H2", "H2", "H2"],
"Headline 3": ["H3", "H3", "H3", "H3"],
"Description 1": ["D1", "D1", "D1", "D1"],
"Description 2": ["D2", "D2", "D2", "D2"],
"Path 1": ["P1", "P1", "P1", "P1"],
"Path 2": ["P2", "P2", "P2", "P2"],
"Final URL": ["URL", "URL", "URL", "URL"],
}
),
None,
),
],
)
def test_validate_output_data(issues_column: Optional[List[str]]) -> None:
df = pd.DataFrame(
{
"Headline 1": ["H1", "H1", "H1", "H1"],
"Headline 2": ["H1", "H2", "H2", ("H" * 31)],
"Headline 3": ["H3", "H3", "H3", ""],
"Description 1": ["D1", "D1", "D2", "D3"],
"Description 2": ["D1", "D1", "D3", ""],
"Path 1": ["P1", "P1", "P1", "P1"],
"Path 2": ["P2", "P2", "P2", "P2"],
"Final URL": ["URL", "URL", "URL", "URL"],
}
)
result = validate_output_data(df, "ad")
def test_validate_output_data(
df: pd.DataFrame, issues_column: Optional[List[str]]
) -> None:
expected = df.copy()
result = validate_output_data(df, "ad")

if issues_column:
expected.insert(0, "Issues", "")
expected["Issues"] = issues_column

assert result.equals(expected)
Loading