Update validation (#102)

google_sheets/app.py

@@ -362,14 +362,6 @@ async def get_all_sheet_titles(
 ]
 
 
-def _validate_target_resource(target_resource: Optional[str]) -> None:
-    if target_resource not in ["ad", "keyword"]:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail="The target resource should be either 'ad' or 'keyword'.",
-        )
-
-
 async def process_campaign_data(
     template_sheet_values: GoogleSheetValues,
     new_campaign_sheet_values: GoogleSheetValues,

google_sheets/data_processing/processing.py

@@ -162,7 +162,7 @@ def _use_template_row(category: Any, template_row: pd.Series) -> bool:
     if not template_row["Category"]:
         return True
 
-    return template_row["Category"] == category  # type: ignore[no-any-return]
+    return template_row["Category"].lower() == str(category).lower()  # type: ignore[no-any-return]
 
 
 def _process_row(
@@ -219,6 +219,7 @@ def _process_row(
 
         final_df = pd.concat([final_df, pd.DataFrame([new_row])], ignore_index=True)
 
+    final_df = final_df.drop_duplicates(ignore_index=True)
     return final_df
 
 

pyproject.toml

@@ -47,7 +47,7 @@ dependencies = [
     "pydantic>=2.3,<3",
     "fastapi>=0.110.2",
     "prisma==0.13.1",
-    "google-api-python-client==2.142.0",
+    "google-api-python-client==2.143.0",
     "asyncify==0.10.0",
     "pandas==2.2.2"
 ]
@@ -66,8 +66,8 @@ lint = [
     "types-ujson",
     "types-Pygments",
     "types-docutils",
-    "mypy==1.11.0",
-    "ruff==0.6.2",
+    "mypy==1.11.2",
+    "ruff==0.6.3",
     "pyupgrade-directories==0.3.0",
     "bandit==1.7.9",
     "semgrep==1.85.0",

tests/data_processing/test_processing.py

@@ -6,6 +6,7 @@
 from google_sheets.data_processing.processing import (
     _copy_all_with_prefixes,
     _get_target_location,
+    _process_row,
     _update_campaign_name,
     _use_template_row,
     _validate_language_codes,
@@ -62,7 +63,7 @@ def test_validate_input_data(df: pd.DataFrame, expected: str) -> None:
         (
             pd.Series(
                 {
-                    "Category": "Bus",
+                    "Category": "bus",
                 }
             ),
             True,
@@ -78,7 +79,7 @@ def test_validate_input_data(df: pd.DataFrame, expected: str) -> None:
         (
             pd.Series(
                 {
-                    "Category": "Ferry",
+                    "Category": "ferry",
                 }
             ),
             False,
@@ -97,6 +98,53 @@ def test_use_template_row(template_row: pd.Series, expected: bool) -> None:
     assert _use_template_row("Bus", template_row) == expected
 
 
+@pytest.mark.parametrize(
+    ("category", "expected_length"),
+    [
+        (
+            "Bus",
+            1,
+        ),
+        (
+            "Ferry",
+            0,
+        ),
+    ],
+)
+def test_process_row(
+    category: str,
+    expected_length: int,
+) -> None:
+    template_row = pd.Series(
+        {
+            "Campaign Name": "USA - A - B - EN",
+            "Ad Group Name": "A - B",
+            "Keyword": "k1",
+            "Max CPC": "",
+            "Language Code": "EN",
+            "Negative": "FALSE",
+            "Level": "",
+            "Keyword Match Type": "Exact",
+            "Match Type": "Exact",
+            "Category": "Bus",
+        }
+    )
+    new_campaign_row = pd.Series(
+        {
+            "Campaign Name": "USA - A - B - EN",
+            "Country": "USA",
+            "Station From": "A",
+            "Station To": "B",
+            "Language Code": "EN",
+            "Category": category,
+        }
+    )
+    final_df = pd.DataFrame(columns=template_row.index)
+    final_df = _process_row(new_campaign_row, template_row, final_df, "keyword")
+
+    assert len(final_df) == expected_length
+
+
 @pytest.mark.parametrize(
     ("merged_campaigns_ad_groups_df", "template_df", "new_campaign_df", "expected"),
     [