Add check for category to flag new/invalid submissions.

.github/workflows/check_categories.yaml

@@ -0,0 +1,25 @@
+name: Check categories
+
+on:
+  pull_request:
+    paths:
+      - "plane-alert-db.csv"
+      - "plane-alert-pia.csv"
+      - "plane-alert-ukraine.csv"
+      - "plane_images.csv"
+
+jobs:
+  checkCategories:
+    runs-on: ubuntu-latest
+    name: Check if main databases have valid Categories
+    steps:
+      - name: Checkout
+        uses: actions/[email protected]
+      - uses: actions/[email protected]
+        with:
+          python-version: "3.10"
+          cache: "pip"
+      - run: pip install -r ./scripts/requirements.txt
+
+      - name: Run main database checks
+        run: python ./scripts/check_categories.py

.github/workflows/create_db_derivatives.yaml

@@ -31,6 +31,9 @@ jobs:
       - name: Create category and images derivative CSV files
         run: python ./scripts/create_db_derivatives.py
 
+      - name: Create valid category listing
+        run: python ./scripts/export_categories.py
+
       - name: Update README.md to include changes
         run: python ./scripts/update_readme.py
 

plane-alert-categories.csv

@@ -0,0 +1,52 @@
+Category
+Other Air Forces
+Toy Soldiers
+Flying Doctors
+Dictator Alert
+Governments
+Ptolemy would be proud
+Police Forces
+Dogs with Jobs
+Quango
+Jump Johnny Jump
+Aerial Firefighter
+Climate Crisis
+Jesus he Knows me
+Big Hello
+Other Navies
+United States Navy
+Coastguard
+Bizjets
+Da Comrade
+Gunship
+As Seen on TV
+Oligarch
+Oxcart
+Distinctive
+Joe Cool
+Don't you know who I am?
+Historic
+You came here in that thing?
+Hired Gun
+Perfectly Serviceable Aircraft
+Gas Bags
+Vanity Plate
+Watch Me Fly
+Zoomies
+GAF
+Special Forces
+Aerobatic Teams
+UAV
+UK National Police Air Service
+RAF
+Royal Navy Fleet Air Arm
+Royal Aircraft
+Army Air Corps
+Football
+Radiohead
+Nuclear
+USAF
+PIA
+CAP
+United States Marine Corps
+Ukraine

scripts/check_categories.py

@@ -0,0 +1,46 @@
+""""script to flag new/invalid categories"""
+
+import logging
+import pandas as pd
+import sys
+
+logging.basicConfig(
+    format="%(asctime)s %(levelname)-8s [%(name)s] %(message)s", level=logging.INFO
+)
+
+if __name__ == "__main__":
+    logging.info("Reading the main csv file...")
+    df = pd.read_csv("plane-alert-db.csv")
+
+    logging.info("Reading the Ukraine csv file...")
+    ukraine_df = pd.read_csv("plane-alert-ukraine.csv")
+
+    category_unique_df = (
+        pd.concat([df["Category"], ukraine_df["Category"]])
+        .drop_duplicates()
+        .reset_index(drop=False)
+    )
+    category_unique_df = category_unique_df.drop('index', axis=1)
+    logging.info(f"Total Categories in PR Count: ({category_unique_df.shape[0]}).")
+
+    logging.info("Reading the export category csv file...")
+    valid_df = pd.read_csv("plane-alert-categories.csv")
+
+    if not valid_df.equals(category_unique_df):
+        logging.info("Invalid category used!")
+        merged_df = valid_df.merge(category_unique_df, indicator=True, how='outer')
+        changed_df = merged_df[merged_df['_merge'] == 'right_only']
+        changed_df = changed_df.drop('_merge', axis=1)
+
+        logging.info(
+            "New Categories found ({}):\n{}".format(
+                changed_df.shape[0],
+                changed_df.to_string(header=False, index=False),
+            )
+        )
+
+        sys.stdout.write(
+            f"The files contain invalid or new Categories:\n"
+        )
+        sys.exit(1)
+    logging.info("Categories check good!")

scripts/export_categories.py

@@ -0,0 +1,31 @@
+""""script to export current categories"""
+
+import logging
+import pandas as pd
+
+logging.basicConfig(
+    format="%(asctime)s %(levelname)-8s [%(name)s] %(message)s", level=logging.INFO
+)
+
+if __name__ == "__main__":
+    logging.info("Reading the main csv file...")
+    df = pd.read_csv("plane-alert-db.csv")
+
+    logging.info("Reading the Ukraine csv file...")
+    ukraine_df = pd.read_csv("plane-alert-ukraine.csv")
+
+    category_unique_df = (
+        pd.concat([df["Category"], ukraine_df["Category"]])
+        .drop_duplicates()
+        .reset_index(drop=True)
+    )
+    logging.info(f"Total Categories Count: ({category_unique_df.shape[0]}).")
+
+    category_unique_df.to_csv(
+    "plane-alert-categories.csv",
+    mode="wb",
+    index=False,
+    header=True,
+    encoding="utf8",
+    lineterminator="\n",
+    )