Initial commit: CSV row filler for satellite metadata

README.md

@@ -0,0 +1,21 @@
+# fill_csv.py
+
+Füllt fehlende ROW-Nummern in einer Satellitenmetadaten-CSV auf.
+
+## Nutzung
+
+```bash
+python fill_csv.py eingabe.csv
+```
+
+Die Ausgabe landet automatisch als `eingabe_filled.csv` im selben Ordner.
+
+Optional kann ein eigener Ausgabepfad angegeben werden:
+
+```bash
+python fill_csv.py eingabe.csv ausgabe.csv
+```
+
+## Was macht das Skript?
+
+Für jede Kombination aus `PATH` und `DATE` schaut das Skript, welche ROW-Nummern vorhanden sind, und füllt die Lücken zwischen Minimum und Maximum mit Platzhalterzeilen auf. Die neuen Zeilen übernehmen die Grunddaten (MISSION, SENSOR, PATH, DATE usw.), alles ab Spalte 10 bleibt leer.

fill_csv.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+"""Fill missing ROW integers within each (PATH, DATE) group of a satellite imagery CSV."""
+
+import csv
+import sys
+from collections import defaultdict
+from pathlib import Path
+
+
+def fill_csv(input_path: Path, output_path: Path) -> None:
+    with open(input_path, newline="", encoding="utf-8") as f:
+        reader = csv.reader(f)
+        header = next(reader)
+        rows = list(reader)
+
+    num_cols = len(header)
+
+    # Group data rows by (PATH, DATE) — columns 3 and 9
+    groups: dict[tuple, list] = defaultdict(list)
+    for row in rows:
+        path_val = row[3]
+        date_val = row[9]
+        groups[(path_val, date_val)].append(row)
+
+    synthetic_rows: list[list[str]] = []
+
+    for (path_val, date_val), group in groups.items():
+        row_numbers = {int(r[4]) for r in group}
+        min_row = min(row_numbers)
+        max_row = max(row_numbers)
+        missing = set(range(min_row, max_row + 1)) - row_numbers
+
+        template = group[0]
+        for r in sorted(missing):
+            new_row = (
+                template[:4]                       # cols 0–3: RECORD_TYP, MISSION, SENSOR, PATH
+                + [str(r)]                         # col 4: ROW
+                + template[5:8]                    # cols 5–7: SCENE, SUB, SHIFT
+                + [f"{template[3]}/{r}"]           # col 8: LABEL
+                + [template[9]]                    # col 9: DATE
+                + [""] * (num_cols - 10)           # cols 10–end: blank
+            )
+            synthetic_rows.append(new_row)
+
+    all_rows = rows + synthetic_rows
+    all_rows.sort(key=lambda r: (r[3], r[9], int(r[4])))
+
+    with open(output_path, "w", newline="", encoding="utf-8") as f:
+        writer = csv.writer(f, quoting=csv.QUOTE_ALL)
+        writer.writerow(header)
+        writer.writerows(all_rows)
+
+    print(f"Original rows : {len(rows)}")
+    print(f"Synthetic rows: {len(synthetic_rows)}")
+    print(f"Total rows    : {len(all_rows)}")
+    print(f"Output written: {output_path}")
+
+
+def main() -> None:
+    if len(sys.argv) < 2:
+        print(f"Usage: {sys.argv[0]} <input.csv> [output.csv]", file=sys.stderr)
+        sys.exit(1)
+
+    input_path = Path(sys.argv[1])
+    if len(sys.argv) >= 3:
+        output_path = Path(sys.argv[2])
+    else:
+        output_path = input_path.with_stem(input_path.stem + "_filled")
+
+    fill_csv(input_path, output_path)
+
+
+if __name__ == "__main__":
+    main()