Sample input for the whole test

database.py

@@ -38,14 +38,25 @@ def adapt_movie_data(data_in: dict):
 
 
 def fill_db(
-    db=SessionLocal(), movie_input_file: str = "input_data/movies_metadata.csv"
+    db=SessionLocal(),
+    movie_input_file: str = "input_data/movies_metadata.csv",
+    sample_rate=100,
 ):
     import crud
     import csv
+    import random
 
     page_size = 1_00
+
+    def compute_rate(*dummy):
+        if 0 < sample_rate < 100:
+            return random.random() < (sample_rate / 100)
+        return True
+
     with open(movie_input_file) as csvfile:
-        for count, movie_data in enumerate(csv.DictReader(csvfile), start=1):
+        for count, movie_data in enumerate(
+            filter(compute_rate, csv.DictReader(csvfile)), start=1
+        ):
             if count % page_size == 0:
                 db.commit()
 
@@ -62,4 +73,4 @@ def fill_db(
 
 if __name__ == "__main__":
     create_db()
-    fill_db()
+    fill_db(sample_rate=1)

utests/test_sql_database.py

@@ -161,7 +161,7 @@ def test_title_is_taken_form_original_title_is_missing():
 
     assert movie_title not in movies_by_title, "The movie should not be pre existing"
     with db_context() as db:
-        fill_db(db, file_path)
+        fill_db(db, file_path, sample_rate=1)
 
     movies = client.get("movies")
     movies_by_title = {m["title"]: m for m in movies.json()}